Arxiv Speech Papers

2026-04-01

Sound 9

☆ FineLAP: Taming Heterogeneous Supervision for Fine-grained Language-Audio Pretraining

Xiquan Li, Xuenan Xu, Ziyang Ma, Wenxi Chen, Haolin He, Qiuqiang Kong, Xie Chen

Contrastively pretrained audio-language models (e.g., CLAP) excel at clip-level understanding but struggle with frame-level tasks. Existing extensions fail to exploit the varying granularity of real-world audio-text data, where massive clip-level textual descriptions coexist with limited frame-level annotations. This paper proposes Fine-grained Language-Audio Pretraining (FineLAP), a novel training paradigm that advances both clip- and frame-level alignment in CLAP with heterogeneous data. FineLAP introduces a dual-stream sigmoid loss with a cluster-based sampling strategy to jointly learn from clip- and frame-level supervision. To capture both global semantics and local details, FineLAP uses a decoupled audio projector on top of a self-supervised encoder. To alleviate the scarcity of temporally annotated data, we present FineLAP-100k, a large-scale synthetic SED dataset constructed through a scalable curation pipeline. Extensive experiments demonstrate that FineLAP achieves SOTA performance across multiple audio understanding tasks, including retrieval, classification, sound event detection, and text-to-audio grounding. Ablation studies further show that coarse- and fine-grained alignment are mutually beneficial, providing insights for building better audio-language models (ALMs).

☆ TRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation Models

Awais Khan, Muhammad Umar Farooq, Kutub Uddin, Khalid Malik

Partial audio deepfakes, where synthesized segments are spliced into genuine recordings, are particularly deceptive because most of the audio remains authentic. Existing detectors are supervised: they require frame-level annotations, overfit to specific synthesis pipelines, and must be retrained as new generative models emerge. We argue that this supervision is unnecessary. We hypothesize that speech foundation models implicitly encode a forensic signal: genuine speech forms smooth, slowly varying embedding trajectories, while splice boundaries introduce abrupt disruptions in frame-level transitions. Building on this, we propose TRACE (Training-free Representation-based Audio Countermeasure via Embedding dynamics), a training-free framework that detects partial audio deepfakes by analyzing the first-order dynamics of frozen speech foundation model representations without any training, labeled data, or architectural modification. We evaluate TRACE on four benchmarks that span two languages using six speech foundation models. In PartialSpoof, TRACE achieves 8.08% EER, competitive with fine-tuned supervised baselines. In LlamaPartialSpoof, the most challenging benchmark featuring LLM-driven commercial synthesis, TRACE surpasses a supervised baseline outright (24.12% vs. 24.49% EER) without any target-domain data. These results show that temporal dynamics in speech foundation models provide an effective, generalize signal for training-free audio forensics.

☆ Sona: Real-Time Multi-Target Sound Attenuation for Noise Sensitivity

Jeremy Zhengqi Huang, Emani Hicks, Sidharth, Gillian R. Hayes, Dhruv Jain

For people with noise sensitivity, everyday soundscapes can be overwhelming. Existing tools such as active noise cancellation reduce discomfort by suppressing the entire acoustic environment, often at the cost of awareness of surrounding people and events. We present Sona, an interactive mobile system for real-time soundscape mediation that selectively attenuates bothersome sounds while preserving desired audio. Sona is built on a target-conditioned neural pipeline that supports simultaneous attenuation of multiple overlapping sound sources, overcoming the single-target limitation of prior systems. It runs in real time on-device and supports user-extensible sound classes through in-situ audio examples, without retraining. Sona is informed by a formative study with 68 noise-sensitive individuals. Through technical benchmarking and an in-situ study with 10 participants, we show that Sona achieves low-latency, multi-target attenuation suitable for live listening, and enables meaningful reductions in bothersome sounds while maintaining awareness of surroundings. These results point toward a new class of personal AI systems that support comfort and social participation by mediating real-world acoustic environments.

comment: 12 pages, 6 figures

♻ ☆ Enhancing Infant Crying Detection with Gradient Boosting for Improved Emotional and Mental Health Diagnostics

Kyunghun Lee, Lauren M. Henry, Eleanor Hansen, Elizabeth Tandilashvili, Lauren S. Wakschlag, Elizabeth Norton, Daniel S. Pine, Melissa A. Brotman, Francisco Pereira

Infant crying can serve as a crucial indicator of various physiological and emotional states. This paper introduces a comprehensive approach detecting infant cries within audio data. We integrate Wav2Vec with traditional audio features and employ Gradient Boosting Machines for cry classification. We validate our approach on a real world dataset, demonstrating significant performance improvements over existing methods.

♻ ☆ Fair-Gate: Fairness-Aware Interpretable Risk Gating for Sex-Fair Voice Biometrics

Yangyang Qu, Massimiliano Todisco, Chiara Galdi, Nicholas Evans

Voice biometric systems can exhibit sex-related performance gaps even when overall verification accuracy is strong. We attribute these gaps to two practical mechanisms: (i) demographic shortcut learning, where speaker classification training exploits spurious correlations between sex and speaker identity, and (ii) feature entanglement, where sex-linked acoustic variation overlaps with identity cues and cannot be removed without degrading speaker discrimination. We propose Fair-Gate, a fairness-aware and interpretable risk-gating framework that addresses both mechanisms in a single pipeline. Fair-Gate applies risk extrapolation to reduce variation in speaker-classification risk across proxy sex groups, and introduces a local complementary gate that routes intermediate features into an identity branch and a sex branch. The gate provides interpretability by producing an explicit routing mask that can be inspected to understand which features are allocated to identity versus sex-related pathways. Experiments on VoxCeleb1 show that Fair-Gate improves the utility--fairness trade-off, yielding more sex-fair ASV performance under challenging evaluation conditions.

♻ ☆ DuoTok: Source-Aware Dual-Track Tokenization for Multi-Track Music Language Modeling

Rui Lin, Zhiyue Wu, Jiahe Le, Kangdi Wang, Weixiong Chen, Junyu Dai, Tao Jiang

Audio tokenization bridges continuous waveforms and multi-track music language models. In dual-track modeling, tokens should preserve three properties at once: high-fidelity reconstruction, strong predictability under a language model, and cross-track correspondence. We introduce DuoTok, a source-aware dual-track tokenizer that addresses this trade-off through staged disentanglement. DuoTok first pretrains a semantic encoder, then regularizes it with multi-task supervision, freezes the encoder, and applies hard dual-codebook routing while keeping auxiliary objectives on quantized codes. A diffusion decoder reconstructs high-frequency details, allowing tokens to focus on structured information for sequence modeling. On standard benchmarks, DuoTok achieves a favorable predictability-fidelity trade-off, reaching the lowest cnBPT while maintaining competitive reconstruction at 0.75 kbps. Under a held-constant dual-track language modeling protocol, enBPT also improves, indicating gains beyond codebook size effects. Controlled diagnostics show larger predictability costs under cross-track corruption and larger gains from longer context, suggesting that models trained on DuoTok tokens use cross-track structure and non-local history.

comment: 17 pages, 5 figures, 8 tables. Project page: https://eps-acoustic-revolution-lab.github.io/DUO_TOK/

♻ ☆ CoDeTT: A Context-Aware Decision Benchmark for Turn-Taking Evaluation

Huan Shen, Yingao Wang, Shangkun Huang, Wei Zou, Yunzhang Chen

Turn-taking modeling is fundamental to spoken dialogue systems, yet its evaluation remains fragmented and often limited to binary boundary detection under narrow interaction settings. Such protocols hinder systematic comparison and obscure model weaknesses across conversational conditions. We present CoDeTT, a context-aware decision benchmark for turn-taking evaluation. CoDeTT formulates turn-taking as a structured decision problem and constructs a multi-scenario dataset with fine-grained decision categories and controlled context variations. Under a unified evaluation protocol, we assess representative existing models and observe substantial performance disparities across decision types and interaction scenarios. CoDeTT provides a standardized benchmark for systematic and context-aware evaluation of turn-taking systems. The benchmark dataset and evaluation toolkit are available at https://yingaowang-casia.github.io/CoDeTT.github.io/.

comment: Submitted to Interspeech 2026

♻ ☆ MATHDance: Mamba-Transformer Architecture with Uniform Tokenization for High-Quality 3D Dance Generation

Kaixing Yang, Xulong Tang, Ziqiao Peng, Yuxuan Hu, Xiangyue Zhang, Puwei Wang, Hongyan Liu, Jun He, Zhaoxin Fan

Music-to-dance generation represents a challenging yet pivotal task at the intersection of choreography, virtual reality, and creative content generation. Despite its significance, existing methods face substantial limitation in achieving choreographic consistency. To address the challenge, we propose MatchDance, a novel framework for music-to-dance generation that constructs a latent representation to enhance choreographic consistency. MatchDance employs a two-stage design: (1) a Kinematic-Dynamic-based Quantization Stage (KDQS), which encodes dance motions into a latent representation by Finite Scalar Quantization (FSQ) with kinematic-dynamic constraints and reconstructs them with high fidelity, and (2) a Hybrid Music-to-Dance Generation Stage(HMDGS), which uses a Mamba-Transformer hybrid architecture to map music into the latent representation, followed by the KDQS decoder to generate 3D dance motions. Additionally, a music-dance retrieval framework and comprehensive metrics are introduced for evaluation. Extensive experiments on the FineDance dataset demonstrate state-of-the-art performance.

♻ ☆ Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability

Xiaoxu Zhu, Junhua Li, Aaron J. Li, Guangchao Yao, Xiaojie Yu

Self-supervised speech models learn representations that capture both content and speaker information. Yet this entanglement creates problems: content tasks suffer from speaker bias, and privacy concerns arise when speaker identity leaks through supposedly anonymized representations. We present two contributions to address these challenges. First, we develop InterpTRQE-SptME (Timbre Residual Quantitative Evaluation Benchmark of Speech pre-training Models Encoding via Interpretability), a benchmark that directly measures residual speaker information in content embeddings using SHAP-based interpretability analysis. Unlike existing indirect metrics, our approach quantifies the exact proportion of speaker information remaining after disentanglement. Second, we propose InterpTF-SptME, which uses these interpretability insights to filter speaker information from embeddings. Testing on VCTK with seven models including HuBERT, WavLM, and ContentVec, we find that SHAP Noise filtering reduces speaker residuals from 18.05% to nearly zero while maintaining recognition accuracy (CTC loss increase under 1%). The method is model-agnostic and requires no retraining.

comment: 5 pages, 4 figures

Audio and Speech Processing 11

☆ Diff-VS: Efficient Audio-Aware Diffusion U-Net for Vocals Separation ICASSP 2026

Yun-Ning, Hung, Richard Vogl, Filip Korzeniowski, Igor Pereira

While diffusion models are best known for their performance in generative tasks, they have also been successfully applied to many other tasks, including audio source separation. However, current generative approaches to music source separation often underperform on standard objective metrics. In this paper, we address this issue by introducing a novel generative vocal separation model based on the Elucidated Diffusion Model (EDM) framework. Our model processes complex short-time Fourier transform spectrograms and employs an improved U-Net architecture based on music-informed design choices. Our approach matches discriminative baselines on objective metrics and achieves perceptual quality comparable to state-of-the-art systems, as assessed by proxy subjective metrics. We hope these results encourage broader exploration of generative methods for music source separation

comment: Accepted at ICASSP 2026

☆ VisG AV-HuBERT: Viseme-Guided AV-HuBERT ICPR 2026

Aristeidis Papadopoulos, Rishabh Jain, Naomi Harte

Audio-Visual Speech Recognition (AVSR) systems nowadays integrate Large Language Model (LLM) decoders with transformer-based encoders, achieving state-of-the-art results. However, the relative contributions of improved language modelling versus enhanced audiovisual encoding remain unclear. We propose Viseme-Guided AV-HuBERT (VisG AV-HuBERT), a multi-task fine-tuning framework that incorporates auxiliary viseme classification to strengthen the model's reliance on visual articulatory features. By extending AV-HuBERT with a lightweight viseme prediction sub-network, this method explicitly guides the encoder to preserve visual speech information. Evaluated on LRS3, VisG AV-HuBERT achieves comparable or improved performance over the baseline AV-HuBERT, with notable gains under heavy noise conditions. WER reduces from 13.59% to 6.60% (51.4% relative improvement) at -10 dB Signal-to-Noise Ratio (SNR) for Speech noise. Deeper analysis reveals substantial reductions in substitution errors across noise types, demonstrating improved speech unit discrimination. Evaluation on LRS2 confirms generalization capability. Our results demonstrate that explicit viseme modelling enhances encoder representations, and provides a foundation for enhancing noise-robust AVSR through encoder-level improvements.

comment: Includes Supplementary Material. Accepted for Publication at International Conference on Pattern Recognition 2026 - ICPR 2026. Code is available at https://github.com/aristosp/visg_avhubert

☆ Description and Discussion on DCASE 2026 Challenge Task 4: Spatial Semantic Segmentation of Sound Scenes

Masahiro Yasuda, Binh Thien Nguyen, Noboru Harada, Romain Serizel, Mayank Mishra, Marc Delcroix, Carlos Hernandez-Olivan, Shoko Araki, Daiki Takeuchi, Tomohiro Nakatani, Nobutaka Ono

This paper presents an overview of the Detection and Classification of Acoustic Scenes and Events (DCASE) 2026 Challenge Task 4, Spatial Semantic Segmentation of Sound Scenes (S5). The S5 task focuses on the joint detection and separation of sound events in complex spatial audio mixtures, contributing to the foundation of immersive communication. First introduced in DCASE 2025, the S5 task continues in DCASE 2026 Task 4 with key changes to better reflect real-world conditions, including allowing mixtures to contain multiple sources of the same class and to contain no target sources. In this paper, we describe task setting, along with the corresponding updates to the evaluation metrics and dataset. The experimental results of the submitted systems are also reported and analyzed. The official access point for data and code is https://github.com/nttcslab/dcase2026_task4_baseline.

☆ OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models

Han Zhu, Lingxuan Ye, Wei Kang, Zengwei Yao, Liyong Guo, Fangjun Kuang, Zhifeng Han, Weiji Zhuang, Long Lin, Daniel Povey

We present OmniVoice, a massive multilingual zero-shot text-to-speech (TTS) model that scales to over 600 languages. At its core is a novel diffusion language model-style discrete non-autoregressive (NAR) architecture. Unlike conventional discrete NAR models that suffer from performance bottlenecks in complex two-stage (text-to-semantic-to-acoustic) pipelines, OmniVoice directly maps text to multi-codebook acoustic tokens. This simplified approach is facilitated by two key technical innovations: (1) a full-codebook random masking strategy for efficient training, and (2) initialization from a pre-trained LLM to ensure superior intelligibility. By leveraging a 581k-hour multilingual dataset curated entirely from open-source data, OmniVoice achieves the broadest language coverage to date and delivers state-of-the-art performance across Chinese, English, and diverse multilingual benchmarks. Our code and pre-trained models are publicly available at https://github.com/k2-fsa/OmniVoice.

♻ ☆ Enhancing Infant Crying Detection with Gradient Boosting for Improved Emotional and Mental Health Diagnostics

Kyunghun Lee, Lauren M. Henry, Eleanor Hansen, Elizabeth Tandilashvili, Lauren S. Wakschlag, Elizabeth Norton, Daniel S. Pine, Melissa A. Brotman, Francisco Pereira

♻ ☆ Fair-Gate: Fairness-Aware Interpretable Risk Gating for Sex-Fair Voice Biometrics

Yangyang Qu, Massimiliano Todisco, Chiara Galdi, Nicholas Evans

♻ ☆ Measuring Prosody Diversity in Zero-Shot TTS: A New Metric, Benchmark, and Exploration ICASSP 2026

Yifan Yang, Bing Han, Hui Wang, Long Zhou, Wei Wang, Mingyu Cui, Xu Tan, Xie Chen

Prosody diversity is essential for achieving naturalness and expressiveness in zero-shot text-to-speech (TTS). However, frequently used acoustic metrics capture only partial views of prosodic variation and correlate poorly with human perception, leaving the problem of reliably quantifying prosody diversity underexplored. To bridge this gap, we introduce ProsodyEval, a prosody diversity assessment dataset that provides Prosody Mean Opinion Score (PMOS) alongside conventional acoustic metrics. ProsodyEval comprises 1000 speech samples derived from 7 mainstream TTS systems, with 2000 human ratings. Building on this, we propose the Discretized Speech Weighted Edit Distance (DS-WED), a new objective diversity metric that quantifies prosodic variation via weighted edit distance over semantic tokens. Experiments on ProsodyEval show that DS-WED achieves substantially higher correlation with human judgments than existing acoustic metrics, while remaining highly robust in speech tokenization from HuBERT and WavLM. Leveraging DS-WED, we benchmark state-of-the-art open-source TTS systems on LibriSpeech test-clean and Seed-TTS test-en, and further explorations uncover several factors that influence prosody diversity, including generative modeling paradigms, duration control, and reinforcement learning. Moreover, we find that current large audio language models (LALMs) remain limited in capturing prosodic variations. Audio samples are available at https://prosodyeval.github.io.

comment: Accepted in ICASSP 2026

♻ ☆ MATHDance: Mamba-Transformer Architecture with Uniform Tokenization for High-Quality 3D Dance Generation

Kaixing Yang, Xulong Tang, Ziqiao Peng, Yuxuan Hu, Xiangyue Zhang, Puwei Wang, Hongyan Liu, Jun He, Zhaoxin Fan

♻ ☆ How Open is Open TTS? A Practical Evaluation of Open Source TTS Tools

Teodora Răgman, Adrian Bogdan Stânea, Horia Cucu, Adriana Stan

Open-source text-to-speech (TTS) frameworks have emerged as highly adaptable platforms for developing speech synthesis systems across a wide range of languages. However, their applicability is not uniform -- particularly when the target language is under-resourced or when computational resources are constrained. In this study, we systematically assess the feasibility of building novel TTS models using four widely adopted open-source architectures: FastPitch, VITS, Grad-TTS, and Matcha-TTS. Our evaluation spans multiple dimensions, including qualitative aspects such as ease of installation, dataset preparation, and hardware requirements, as well as quantitative assessments of synthesis quality for Romanian. We employ both objective metrics and subjective listening tests to evaluate intelligibility, speaker similarity, and naturalness of the generated speech. The results reveal significant challenges in tool chain setup, data preprocessing, and computational efficiency, which can hinder adoption in low-resource contexts. By grounding the analysis in reproducible protocols and accessible evaluation criteria, this work aims to inform best practices and promote more inclusive, language-diverse TTS development. All information needed to reproduce this study (i.e. code and data) are available in our git repository: https://gitlab.com/opentts_ragman/OpenTTS

comment: Published in IEEE Access https://ieeexplore.ieee.org/document/11269795

♻ ☆ Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability

Xiaoxu Zhu, Junhua Li, Aaron J. Li, Guangchao Yao, Xiaojie Yu

comment: 5 pages, 4 figures

♻ ☆ Robust Residual Finite Scalar Quantization for Neural Compression

Xiaoxu Zhu, Xiaojie Yu, Guangchao Yao, Yiming Ren, Baoxiang Li

Finite Scalar Quantization (FSQ) offers simplified training but suffers from residual magnitude decay in multi-stage settings, where subsequent stages receive exponentially weaker signals. We propose Robust Residual Finite Scalar Quantization (RFSQ), addressing this fundamental limitation through two novel conditioning strategies: learnable scaling factors and invertible layer normalization. Our experiments across audio and image modalities demonstrate RFSQ's effectiveness and generalizability. In audio reconstruction at 24 bits/frame, RFSQ-LayerNorm achieves 3.646 DNSMOS, a 3.6% improvement over state-of-the-art RVQ (3.518). On ImageNet, RFSQ achieves 0.102 L1 loss and 0.100 perceptual loss, with LayerNorm providing 9.7% L1 improvement and 17.4% perceptual improvement over unconditioned variants. The LayerNorm strategy consistently outperforms alternatives by maintaining normalized input statistics across stages, effectively preventing exponential magnitude decay that limits naive residual approaches. RFSQ combines FSQ's simplicity with multi-stage quantization's representational power, establishing a new standard for neural compression across diverse modalities.

comment: 5 pages, 2 figures

2026-03-31

Sound 15

☆ Covertly improving intelligibility with data-driven adaptations of speech timing

Paige Tuttösí, Angelica Lim, H. Henny Yeung, Yue Wang, Jean-Julien Aucouturier

Human talkers often address listeners with language-comprehension challenges, such as hard-of-hearing or non-native adults, by globally slowing down their speech. However, it remains unclear whether this strategy actually makes speech more intelligible. Here, we take advantage of recent advancements in machine-generated speech allowing more precise control of speech rate in order to systematically examine how targeted speech-rate adjustments may improve comprehension. We first use reverse-correlation experiments to show that the temporal influence of speech rate prior to a target vowel contrast (ex. the tense-lax distinction) in fact manifests in a scissor-like pattern, with opposite effects in early versus late context windows; this pattern is remarkably stable both within individuals and across native L1-English listeners and L2-English listeners with French, Mandarin, and Japanese L1s. Second, we show that this speech rate structure not only facilitates L2 listeners' comprehension of the target vowel contrast, but that native listeners also rely on this pattern in challenging acoustic conditions. Finally, we build a data-driven text-to-speech algorithm that replicates this temporal structure on novel speech sequences. Across a variety of sentences and vowel contrasts, listeners remained unaware that such targeted slowing improved word comprehension. Strikingly, participants instead judged the common strategy of global slowing as clearer, even though it actually increased comprehension errors. Together, these results show that targeted adjustments to speech rate significantly aid intelligibility under challenging conditions, while often going unnoticed. More generally, this paper provides a data-driven methodology to improve the accessibility of machine-generated speech which can be extended to other aspects of speech comprehension and a wide variety of listeners and environments.

☆ SIREN: Spatially-Informed Reconstruction of Binaural Audio with Vision ICASSP 2026

Mingyeong Song, Seoyeon Ko, Junhyug Noh

Binaural audio delivers spatial cues essential for immersion, yet most consumer videos are monaural due to capture constraints. We introduce SIREN, a visually guided mono to binaural framework that explicitly predicts left and right channels. A ViT-based encoder learns dual-head self-attention to produce a shared scene map and end-to-end L/R attention, replacing hand-crafted masks. A soft, annealed spatial prior gently biases early L/R grounding, and a two-stage, confidence-weighted waveform-domain fusion (guided by mono reconstruction and interaural phase consistency) suppresses crosstalk when aggregating multi-crop and overlapping windows. Evaluated on FAIR-Play and MUSIC-Stereo, SIREN yields consistent gains on time-frequency and phase-sensitive metrics with competitive SNR. The design is modular and generic, requires no task-specific annotations, and integrates with standard audio-visual pipelines.

comment: 5 pages, 1 figure, to appear in ICASSP 2026

☆ A Comprehensive Corpus of Biomechanically Constrained Piano Chords: Generation, Analysis, and Implications for Voicing and Psychoacoustics

Mahesh Ramani

I present the generation and analysis of the largest known open-source corpus of playable piano chords (approximately 19.3 million entries). This dataset enumerates the two-handed search space subject to biomechanical constraints (two hands, each with 1.5 octave reach) to an unprecedented extent. To demonstrate the corpus's utility, the relationship between voicing shape and psychoacoustic targets was modeled. Harmonicity proved intrinsic to pitch-class identity: voicing statistics added negligible variance ($ΔR^2 \approx 0.014\%$, $p \approx 0.13$). Conversely, voicing significantly predicted dissonance ($ΔR^2 \approx 6.75\%$, $p \approx 0.0008$). Crucially, skewness ($β\approx +0.145$) was approximately 5.8$\times$ more effective than spread ($β\approx -0.025$) at predicting roughness. The analysis challenges the pedagogical emphasis on ``spread'': skewness is a stronger predictor of dissonance than spread. This suggests that clarity in ``open voicings'' is driven less by width than by negative skewness; achieving lower-register clearance by placing wide gaps at the bottom and allowing tighter clustering in the treble. The results demonstrate the corpus's ability to enable future research, especially in areas such as generative modeling, voice-leading topology, and psychoacoustic analysis.

comment: 10 pages, 3 figures

☆ LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Space

Detai Xin, Shujie Hu, Chengzuo Yang, Chen Huang, Guoqiao Yu, Guanglu Wan, Xunliang Cai

We present LongCat-AudioDiT, a novel, non-autoregressive diffusion-based text-to-speech (TTS) model that achieves state-of-the-art (SOTA) performance. Unlike previous methods that rely on intermediate acoustic representations such as mel-spectrograms, the core innovation of LongCat-AudioDiT lies in operating directly within the waveform latent space. This approach effectively mitigates compounding errors and drastically simplifies the TTS pipeline, requiring only a waveform variational autoencoder (Wav-VAE) and a diffusion backbone. Furthermore, we introduce two critical improvements to the inference process: first, we identify and rectify a long-standing training-inference mismatch; second, we replace traditional classifier-free guidance with adaptive projection guidance to elevate generation quality. Experimental results demonstrate that, despite the absence of complex multi-stage training pipelines or high-quality human-annotated datasets, LongCat-AudioDiT achieves SOTA zero-shot voice cloning performance on the Seed benchmark while maintaining competitive intelligibility. Specifically, our largest variant, LongCat-AudioDiT-3.5B, outperforms the previous SOTA model (Seed-TTS), improving the speaker similarity (SIM) scores from 0.809 to 0.818 on Seed-ZH, and from 0.776 to 0.797 on Seed-Hard. Finally, through comprehensive ablation studies and systematic analysis, we validate the effectiveness of our proposed modules. Notably, we investigate the interplay between the Wav-VAE and the TTS backbone, revealing the counterintuitive finding that superior reconstruction fidelity in the Wav-VAE does not necessarily lead to better overall TTS performance. Code and model weights are released to foster further research within the speech community.

comment: Code and model weights are available at https://github.com/meituan-longcat/LongCat-AudioDiT

☆ Real-Time Band-Grouped Vocal Denoising Using Sigmoid-Driven Ideal Ratio Masking

Daniel Williams

Real-time, deep learning-based vocal denoising has seen significant progress over the past few years, demonstrating the capability of artificial intelligence in preserving the naturalness of the voice while increasing the signal-to-noise ratio (SNR). However, many deep learning approaches have high amounts of latency and require long frames of context, making them difficult to configure for live applications. To address these challenges, we propose a sigmoid-driven ideal ratio mask trained with a spectral loss to encourage an increased SNR and maximized perceptual quality of the voice. The proposed model uses a band-grouped encoder-decoder architecture with frequency attention and achieves a total latency of less than 10,ms, with PESQ-WB improvements of 0.21 on stationary noise and 0.12 on nonstationary noise.

☆ Audio Hallucination Attacks: Probing the Reliability of Large Audio Language Models

Ashish Seth, Sonal Kumar, Ramaneswaran Selvakumar, Nishit Anand, Utkarsh Tyagi, Prem Seetharaman, Ramani Duraiswami, Dinesh Manocha

Large Audio Language Models (LALMs) achieve strong performance on audio-language tasks; however, their reliability in real-world settings remains underexplored. We introduce Audio Hallucination Attacks (AHA), an attack suite called AHA-Eval, comprising 6.5K QA pairs designed to test whether LALMs genuinely ground their responses in the audio input. AHA targets two attack surfaces: (i) query-based attacks, which exploit question structure to induce hallucinations about absent sounds, and (ii) audio-based attacks, which inject synthetic speech describing non-existent events into the audio stream. Evaluating state-of-the-art LALMs, including Audio Flamingo 3 and Gemini 3 Pro, we observe high attack success rates of 95.35% and 79.65%, respectively, revealing a reliability gap that is hidden by standard benchmark performance. To mitigate this, we propose a 120K QA post-alignment dataset, AHA-Guard, which successfully reduces attack success rates by up to 49%.

☆ Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition INTERSPEECH2026

Lukuang Dong, Ziwei Li, Saierdaer Yusuyin, Xianyu Zhao, Zhijian Ou

Phoneme-based ASR factorizes recognition into speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G), enabling cross-lingual acoustic sharing while keeping language-specific orthography in a separate module. While large language models (LLMs) are promising for P2G, multilingual P2G remains challenging due to language-aware generation and severe cross-language data imbalance. We study multilingual LLM-based P2G on the ten-language CV-Lang10 benchmark. We examine robustness strategies that account for S2P uncertainty, including DANP and Simplified SKM (S-SKM). S-SKM is a Monte Carlo approximation that avoids CTC-based S2P probability weighting in P2G training. Robust training and low-resource oversampling reduce the average WER from 10.56% to 7.66%.

comment: Update after INTERSPEECH2026 submission

☆ Asymmetric Encoder-Decoder Based on Time-Frequency Correlation for Speech Separation

Ui-Hyeop Shin, Hyung-Min Park

Speech separation in realistic acoustic environments remains challenging because overlapping speakers, background noise, and reverberation must be resolved simultaneously. Although recent time-frequency (TF) domain models have shown strong performance, most still rely on late-split architectures, where speaker disentanglement is deferred to the final stage, creating an information bottleneck and weakening discriminability under adverse conditions. To address this issue, we propose SR-CorrNet, an asymmetric encoder-decoder framework that introduces the separation-reconstruction (SepRe) strategy into a TF dual-path backbone. The encoder performs coarse separation from mixture observations, while the weight-shared decoder progressively reconstructs speaker-discriminative features with cross-speaker interaction, enabling stage-wise refinement. To complement this architecture, we formulate speech separation as a structured correlation-to-filter problem: spatio-spectro-temporal correlations computed from the observations are used as input features, and the corresponding deep filters are estimated to recover target signals. We further incorporate an attractor-based dynamic split module to adapt the number of output streams to the actual speaker configuration. Experimental results on WSJ0-2/3/4/5Mix, WHAMR!, and LibriCSS demonstrate consistent improvements across anechoic, noisy-reverberant, and real-recorded conditions in both single- and multi-channel settings, highlighting the effectiveness of TF-domain SepRe with correlation-based filter estimation for speech separation.

comment: Submitted to IEEE/ACM Transactions on Audio, Speech, and Language Processing (T-ASLP)

☆ IQRA 2026: Interspeech Challenge on Automatic Assessment Pronunciation for Modern Standard Arabic (MSA)

Yassine El Kheir, Amit Meghanani, Mostafa Shahin, Omnia Ibrahim, Shammur Absar Chowdhury, Nada AlMarwani, Youssef Elshahawy, Ahmed Ali

We present the findings of the second edition of the IQRA Interspeech Challenge, a challenge on automatic Mispronunciation Detection and Diagnosis (MDD) for Modern Standard Arabic (MSA). Building on the previous edition, this iteration introduces \textbf{Iqra\_Extra\_IS26}, a new dataset of authentic human mispronounced speech, complementing the existing training and evaluation resources. Submitted systems employed a diverse range of approaches, spanning CTC-based self-supervised learning models, two-stage fine-tuning strategies, and using large audio-language models. Compared to the first edition, we observe a substantial jump of \textbf{0.28 in F1-score}, attributable both to novel architectures and modeling strategies proposed by participants and to the additional authentic mispronunciation data made available. These results demonstrate the growing maturity of Arabic MDD research and establish a stronger foundation for future work in Arabic pronunciation assessment.

comment: 5 pages paper

☆ Vocal Prognostic Digital Biomarkers in Monitoring Chronic Heart Failure: A Longitudinal Observational Study

Fan Wu, Matthias P. Nägele, Daryush D. Mehta, Elgar Fleisch, Frank Ruschitzka, Andreas J. Flammer, Filipe Barata

Objective: This study aimed to evaluate which voice features can predict health deterioration in patients with chronic HF. Background: Heart failure (HF) is a chronic condition with progressive deterioration and acute decompensations, often requiring hospitalization and imposing substantial healthcare and economic burdens. Current standard-of-care (SoC) home monitoring, such as weight tracking, lacks predictive accuracy and requires high patient engagement. Voice is a promising non-invasive biomarker, though prior studies have mainly focused on acute HF stages. Methods: In a 2-month longitudinal study, 32 patients with HF collected daily voice recordings and SoC measures of weight and blood pressure at home, with biweekly questionnaires for health status. Acoustic analysis generated detailed vowel and speech features. Time-series features were extracted from aggregated lookback windows (e.g., 7 days) to predict next-day health status. Explainable machine learning with nested cross-validation identified top vocal biomarkers, and a case study illustrated model application. Results: A total of 21,863 recordings were analyzed. Acoustic vowel features showed strong correlations with health status. Time-series voice features within the lookback window outperformed corresponding standard care measures, achieving peak sensitivity and specificity of 0.826 and 0.782 versus 0.783 and 0.567 for SoC metrics. Key prognostic voice features identifying deterioration included delayed energy shift, low energy variability, and higher shimmer variability in vowels, along with reduced speaking and articulation rate, lower phonation ratio, decreased voice quality, and increased formant variability in speech. Conclusion: Voice-based monitoring offers a non-invasive approach to detect early health changes in chronic HF, supporting proactive and personalized care.

☆ MambaVoiceCloning: Efficient and Expressive Text-to-Speech via State-Space Modeling and Diffusion Control ICLR 2026

Sahil Kumar, Namrataben Patel, Honggang Wang, Youshan Zhang

MambaVoiceCloning (MVC) asks whether the conditioning path of diffusion-based TTS can be made fully SSM-only at inference, removing all attention and explicit RNN-style recurrence layers across text, rhythm, and prosody, while preserving or improving quality under controlled conditions. MVC combines a gated bidirectional Mamba text encoder, a Temporal Bi-Mamba supervised by a lightweight alignment teacher discarded after training, and an Expressive Mamba with AdaLN modulation, yielding linear-time O(T) conditioning with bounded activation memory and practical finite look-ahead streaming. Unlike prior Mamba-TTS systems that remain hybrid at inference, MVC removes attention-based duration and style modules under a fixed StyleTTS2 mel-diffusion-vocoder backbone. Trained on LJSpeech/LibriTTS and evaluated on VCTK, CSS10 (ES/DE/FR), and long-form Gutenberg passages, MVC achieves modest but statistically reliable gains over StyleTTS2, VITS, and Mamba-attention hybrids in MOS/CMOS, F0 RMSE, MCD, and WER, while reducing encoder parameters to 21M and improving throughput by 1.6x. Diffusion remains the dominant latency source, but SSM-only conditioning improves memory footprint, stability, and deployability.

comment: Accepted at ICLR 2026

♻ ☆ Audio Language Model for Deepfake Detection Grounded in Acoustic Chain-of-Thought

Runkun Chen, Yixiong Fang, Pengyu Chang, Yuante Li, Massa Baali, Bhiksha Raj

Deepfake speech detection systems are often limited to binary classification tasks and struggle to generate interpretable reasoning or provide context-rich explanations for their decisions. These models primarily extract latent embeddings for authenticity detection but fail to leverage structured acoustic evidence such as prosodic, spectral, and physiological attributes in a meaningful manner. This paper introduces CoLMbo-DF, a Feature-Guided Audio Language Model that addresses these limitations by integrating robust deepfake detection with explicit acoustic chain-of-thought reasoning. By injecting structured textual representations of low-level acoustic features directly into the model prompt, our approach grounds the model's reasoning in interpretable evidence and improves detection accuracy. To support this framework, we introduce a novel dataset of audio pairs paired with chain-of-thought annotations. Experiments show that our method, trained on a lightweight open-source language model, significantly outperforms existing audio language model baselines despite its smaller scale, marking a significant advancement in explainable deepfake speech detection.

♻ ☆ Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis

Yushen Chen, Junzhe Liu, Yujie Tu, Zhikang Niu, Yuzhe Liang, Chunyu Qiang, Chen Zhang, Kai Yu, Xie Chen

Arabic spans over 30 spoken varieties, yet no open-source text-to-speech system unifies them. Key barriers include substantial cross-dialect lexical and phonological divergence, scarce synthesis-grade data, and the absence of a standardized multi-dialect evaluation benchmark. We present Habibi, a unified-dialectal Arabic TTS framework that addresses all three. Through a multi-step curation pipeline, we repurpose open-source ASR corpora into TTS training data covering 12+ regional dialects. A linguistically-informed curriculum learning strategy - progressing from Modern Standard Arabic to dialectal data - enables robust zero-shot synthesis without text diacritization. We further release the first standardized multi-dialect Arabic TTS benchmark, comprising over 11,000 utterances across 7 dialect subsets with manually verified transcripts. On this benchmark, our unified model matches or surpasses per-dialect specialized models. Both automatic metrics and human evaluations confirm that Habibi is highly competitive with ElevenLabs' Eleven v3 (alpha) in intelligibility, speaker similarity, and naturalness. Extensive ablations (~8,000 H100 GPU hours, 30+ configurations) validate each design choice. We open-source all checkpoints, training and inference code, and benchmark data - the first such release for multi-dialect Arabic TTS - at https://SWivid.github.io/Habibi/ .

♻ ☆ EchoMark: Perceptual Acoustic Environment Transfer with Watermark-Embedded Room Impulse Response

Chenpei Huang, Lingfeng Yao, Kyu In Lee, Lan Emily Zhang, Xun Chen, Miao Pan

Acoustic Environment Matching (AEM) is the task of transferring clean audio into a target acoustic environment, enabling engaging applications such as audio dubbing and auditory immersive virtual reality (VR). Recovering similar room impulse response (RIR) directly from reverberant speech offers more accessible and flexible AEM solution. However, this capability also introduces vulnerabilities of arbitrary ``relocation" if misused by malicious user, such as facilitating advanced voice spoofing attacks or undermining the authenticity of recorded evidence. To address this issue, we propose EchoMark, the first deep learning-based AEM framework that generates perceptually similar RIRs with embedded watermark. Our design tackle the challenges posed by variable RIR characteristics, such as different durations and energy decays, by operating in the latent domain. By jointly optimizing the model with a perceptual loss for RIR reconstruction and a loss for watermark detection, EchoMark achieves both high-quality environment transfer and reliable watermark recovery. Experiments on diverse datasets validate that EchoMark achieves room acoustic parameter matching performance comparable to FiNS, the state-of-the-art RIR estimator. Furthermore, a high Mean Opinion Score (MOS) of 4.22 out of 5, watermark detection accuracy exceeding 99\%, and bit error rates (BER) below 0.3\% collectively demonstrate the effectiveness of EchoMark in preserving perceptual quality while ensuring reliable watermark embedding.

♻ ☆ POTSA: A Cross-Lingual Speech Alignment Framework for Speech-to-Text Translation

Xuanchen Li, Chenrui Cui, Tianrui Wang, Meng Ge, Zikang Huang, Yizhou Peng, Jin Li, Yuheng Lu, Yu Jiang, Nyima Tashi, Longbiao Wang, Jianwu Dang

Speech Large Language Models have achieved breakthroughs in multilingual speech-to-text translation. However, existing approaches often overlook semantic commonalities across source languages, leading to biased translation performance. In this work, we propose POTSA (Parallel Optimal Transport for Speech Alignment), a new framework based on cross-lingual parallel speech pairs and Optimal Transport, designed to bridge high- and low-resource translation gaps. First, we introduce a Bias Compensation module to coarsely align initial speech representations. Second, we impose token-level OT constraints on a Q-Former using parallel pairs to establish fine-grained representation consistency. Then, we apply a layer scheduling strategy to focus OT constraints on semantically beneficial layers. Experiments on FLEURS show our method achieves SOTA performance, with +1.29 BLEU over five common languages and +2.93 BLEU on zero-shot languages, using only 10 hours of parallel speech per language.

Audio and Speech Processing 9

☆ An Information-Theoretic Method for Dynamic System Identification With Output-Only Damping Estimation

Marios Impraimakis, Feiyu Zhou, Andrew Plummer

The system identification capabilities of a novel information-theoretic method are examined here. Specifically, this work uses information-theoretic metrics and vibration-based measurements to enhance damping estimation accuracy in mechanical systems. The method refers to a key limitation in system identification, signal processing, monitoring, and alert systems. These systems integrate various components, including sensors, data acquisition devices, and alert mechanisms. They are designed to operate in an environment to calculate key parameters such as peak accelerations and duration of high acceleration values. The current operational modal identification methods, though, suffer from limitations related to obtaining poor damping estimates due to their empirical nature. This has a significant impact on alert warning systems. This occurs when their duration is misestimated; specifically, when using the vibration amplitudes as an indicator of danger alerts for monitoring systems in damage or anomaly detection scenarios. To this end, approaches based on the Shannon entropy and the Kullback-Leibler divergence concept are proposed. The primary objective is to monitor the vibration levels in near real-time and provide immediate alerts when predefined thresholds are exceeded. In considering the proposed approach, both new real-world data from the multi-axis simulation table at the University of Bath, as well as the benchmark International Association for Structural Control-American Society of Civil Engineers (IASC-ASCE) structural health monitoring problem are considered. Importantly, the approach is shown to select the optimal model, which accurately captures the correct alert duration, providing a powerful tool for system identification and monitoring.

comment: 18 pages, 16 figures, 4 tables. Published in Journal of Dynamic Systems, Measurement, and Control (ASME), 2026. Licensed under CC BY 4.0

☆ A Comprehensive Corpus of Biomechanically Constrained Piano Chords: Generation, Analysis, and Implications for Voicing and Psychoacoustics

Mahesh Ramani

comment: 10 pages, 3 figures

☆ LongCat-AudioDiT: High-Fidelity Diffusion Text-to-Speech in the Waveform Latent Space

Detai Xin, Shujie Hu, Chengzuo Yang, Chen Huang, Guoqiao Yu, Guanglu Wan, Xunliang Cai

comment: Code and model weights are available at https://github.com/meituan-longcat/LongCat-AudioDiT

☆ Advancing LLM-based phoneme-to-grapheme for multilingual speech recognition INTERSPEECH2026

Lukuang Dong, Ziwei Li, Saierdaer Yusuyin, Xianyu Zhao, Zhijian Ou

comment: Update after INTERSPEECH2026 submission

☆ Asymmetric Encoder-Decoder Based on Time-Frequency Correlation for Speech Separation

Ui-Hyeop Shin, Hyung-Min Park

comment: Submitted to IEEE/ACM Transactions on Audio, Speech, and Language Processing (T-ASLP)

☆ IQRA 2026: Interspeech Challenge on Automatic Assessment Pronunciation for Modern Standard Arabic (MSA)

Yassine El Kheir, Amit Meghanani, Mostafa Shahin, Omnia Ibrahim, Shammur Absar Chowdhury, Nada AlMarwani, Youssef Elshahawy, Ahmed Ali

comment: 5 pages paper

♻ ☆ Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis

Yushen Chen, Junzhe Liu, Yujie Tu, Zhikang Niu, Yuzhe Liang, Chunyu Qiang, Chen Zhang, Kai Yu, Xie Chen

♻ ☆ VAANI: Capturing the language landscape for an inclusive digital India

Sujith Pulikodan, Abhayjeet Singh, Agneedh Basu, Nihar Desai, Pavan Kumar J, Pranav D Bhat, Raghu Dharmaraju, Ritika Gupta, Sathvik Udupa, Saurabh Kumar, Sumit Sharma, Vaibhav Vishwakarma, Visruth Sanka, Dinesh Tewari, Harsh Dhand, Amrita Kamat, Sukhwinder Singh, Shikhar Vashishth, Partha Talukdar, Raj Acharya, Prasanta Kumar Ghosh

Project VAANI is an initiative to create an India-representative multi-modal dataset that comprehensively maps India's linguistic diversity, starting with 165 districts across the country in its first two phases. Speech data is collected through a carefully structured process that uses image-based prompts to encourage spontaneous responses. Images are captured through a separate process that encompasses a broad range of topics, gathered from both within and across districts. The collected data undergoes a rigorous multi-stage quality evaluation, including both automated and manual checks to ensure highest possible standards in audio quality and transcription accuracy. Following this thorough validation, we have open-sourced around 289K images, approximately 31,270 hours of audio recordings, and around 2,067 hours of transcribed speech, encompassing 112 languages from 165 districts from 31 States and Union territories. Notably, significant of these languages are being represented for the first time in a dataset of this scale, making the VAANI project a groundbreaking effort in preserving and promoting linguistic inclusivity. This data can be instrumental in building inclusive speech models for India, and in advancing research and development across speech, image, and multimodal applications.

♻ ☆ EchoMark: Perceptual Acoustic Environment Transfer with Watermark-Embedded Room Impulse Response

Chenpei Huang, Lingfeng Yao, Kyu In Lee, Lan Emily Zhang, Xun Chen, Miao Pan

2026-03-30

Sound 17

☆ SonoWorld: From One Image to a 3D Audio-Visual Scene CVPR 2026

Derong Jin, Xiyi Chen, Ming C. Lin, Ruohan Gao

Tremendous progress in visual scene generation now turns a single image into an explorable 3D world, yet immersion remains incomplete without sound. We introduce Image2AVScene, the task of generating a 3D audio-visual scene from a single image, and present SonoWorld, the first framework to tackle this challenge. From one image, our pipeline outpaints a 360° panorama, lifts it into a navigable 3D scene, places language-guided sound anchors, and renders ambisonics for point, areal, and ambient sources, yielding spatial audio aligned with scene geometry and semantics. Quantitative evaluations on a newly curated real-world dataset and a controlled user study confirm the effectiveness of our approach. Beyond free-viewpoint audio-visual rendering, we also demonstrate applications to one-shot acoustic learning and audio-visual spatial source separation. Project website: https://humathe.github.io/sonoworld/

comment: Accepted by CVPR 2026, project page: https://humathe.github.io/sonoworld/

☆ ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining

Anuj Diwan, Eunsol Choi, David Harwath

We introduce ParaSpeechCLAP, a dual-encoder contrastive model that maps speech and text style captions into a common embedding space, supporting a wide range of intrinsic (speaker-level) and situational (utterance-level) descriptors (such as pitch, texture and emotion) far beyond the narrow set handled by existing models. We train specialized ParaSpeechCLAP-Intrinsic and ParaSpeechCLAP-Situational models alongside a unified ParaSpeechCLAP-Combined model, finding that specialization yields stronger performance on individual style dimensions while the unified model excels on compositional evaluation. We further show that ParaSpeechCLAP-Intrinsic benefits from an additional classification loss and class-balanced training. We demonstrate our models' performance on style caption retrieval, speech attribute classification and as an inference-time reward model that improves style-prompted TTS without additional training. ParaSpeechCLAP outperforms baselines on most metrics across all three applications. Our models and code are released at https://github.com/ajd12342/paraspeechclap .

comment: Under review

☆ Constructing Composite Features for Interpretable Music-Tagging ICASSP 2026

Chenhao Xue, Weitao Hu, Joyraj Chakraborty, Zhijin Guo, Kang Li, Tianyu Shi, Martin Reed, Nikolaos Thomos

Combining multiple audio features can improve the performance of music tagging, but common deep learning-based feature fusion methods often lack interpretability. To address this problem, we propose a Genetic Programming (GP) pipeline that automatically evolves composite features by mathematically combining base music features, thereby capturing synergistic interactions while preserving interpretability. This approach provides representational benefits similar to deep feature fusion without sacrificing interpretability. Experiments on the MTG-Jamendo and GTZAN datasets demonstrate consistent improvements compared to state-of-the-art systems across base feature sets at different abstraction levels. It should be noted that most of the performance gains are noticed within the first few hundred GP evaluations, indicating that effective feature combinations can be identified under modest search budgets. The top evolved expressions include linear, nonlinear, and conditional forms, with various low-complexity solutions at top performance aligned with parsimony pressure to prefer simpler expressions. Analyzing these composite features further reveals which interactions and transformations tend to be beneficial for tagging, offering insights that remain opaque in black-box deep models.

comment: 5 pages, 8 figures, accepted at ICASSP 2026

☆ A Probabilistic Generative Model for Spectral Speech Enhancement

Marco Hidalgo-Araya, Raphaël Trésor, Bart Van Erp, Wouter W. L. Nuijten, Thijs Van De Laar, Bert De Vries

Speech enhancement in hearing aids remains a difficult task in nonstationary acoustic environments, mainly because current signal processing algorithms rely on fixed, manually tuned parameters that cannot adapt in situ to different users or listening contexts. This paper introduces a unified modular framework that formulates signal processing, learning, and personalization as Bayesian inference with explicit uncertainty tracking. The proposed framework replaces ad hoc algorithm design with a single probabilistic generative model that continuously adapts to changing acoustic conditions and user preferences. It extends spectral subtraction with principled mechanisms for in-situ personalization and adaptation to acoustic context. The system is implemented as an interconnected probabilistic state-space model, and inference is performed via variational message passing in the \texttt{RxInfer.jl} probabilistic programming environment, enabling real-time Bayesian processing under hearing-aid constraints. Proof-of-concept experiments on the \emph{VoiceBank+DEMAND} corpus show competitive speech quality and noise reduction with 85 effective parameters. The framework provides an interpretable, data-efficient foundation for uncertainty-aware, adaptive hearing-aid processing and points toward devices that learn continuously through probabilistic inference.

comment: Submitted to the IEEE Open Journal of Signal Processing

☆ Membership Inference Attacks against Large Audio Language Models

Jia-Kai Dong, Yu-Xiang Lin, Hung-Yi Lee

We present the first systematic Membership Inference Attack (MIA) evaluation of Large Audio Language Models (LALMs). As audio encodes non-semantic information, it induces severe train and test distribution shifts and can lead to spurious MIA performance. Using a multi-modal blind baseline based on textual, spectral, and prosodic features, we demonstrate that common speech datasets exhibit near-perfect train/test separability (AUC approximately 1.0) even without model inference, and the standard MIA scores strongly correlate with these blind acoustic artifacts (correlation greater than 0.7). Using this blind baseline, we identify that distribution-matched datasets enable reliable MIA evaluation without distribution shift confounds. We benchmark multiple MIA methods and conduct modality disentanglement experiments on these datasets. The results reveal that LALM memorization is cross-modal, arising only from binding a speaker's vocal identity with its text. These findings establish a principled standard for auditing LALMs beyond spurious correlations.

comment: submitted to Interspeech 2026

☆ On the Usefulness of Diffusion-Based Room Impulse Response Interpolation to Microphone Array Processing

Sagi Della Torre, Mirco Pezzoli, Fabio Antonacci, Sharon Gannot

Room Impulse Responses estimation is a fundamental problem in spatial audio processing and speech enhancement. In this paper, we build upon our previously introduced diffusion-based inpainting framework for Room Impulse Response interpolation and demonstrate its applicability to enhancing the performance of practical multi-microphone array processing tasks. Furthermore, we validate the robustness of this method in interpolating real-world Room Impulse Responses.

☆ MOSS-VoiceGenerator: Create Realistic Voices with Natural Language Descriptions

Kexin Huang, Liwei Fan, Botian Jiang, Yaozhou Jiang, Qian Tu, Jie Zhu, Yuqian Zhang, Yiwei Zhao, Chenchen Yang, Zhaoye Fei, Shimin Li, Xiaogui Yang, Qinyuan Cheng, Xipeng Qiu

Voice design from natural language aims to generate speaker timbres directly from free-form textual descriptions, allowing users to create voices tailored to specific roles, personalities, and emotions. Such controllable voice creation benefits a wide range of downstream applications-including storytelling, game dubbing, role-play agents, and conversational assistants, making it a significant task for modern Text-to-Speech models. However, existing models are largely trained on carefully recorded studio data, which produces speech that is clean and well-articulated, yet lacks the lived-in qualities of real human voices. To address these limitations, we present MOSS-VoiceGenerator, an open-source instruction-driven voice generation model that creates new timbres directly from natural language prompts. Motivated by the hypothesis that exposure to real-world acoustic variation produces more perceptually natural voices, we train on large-scale expressive speech data sourced from cinematic content. Subjective preference studies demonstrate its superiority in overall performance, instruction-following, and naturalness compared to other voice design models.

☆ Audio Language Model for Deepfake Detection Grounded in Acoustic Chain-of-Thought

Runkun Chen, Yixiong Fang, Pengyu Chang, Yuante Li, Massa Baali, Bhiksha Ramakrishnan

☆ On the Role of Encoder Depth: Pruning Whisper and LoRA Fine-Tuning in SLAM-ASR SP

Ganesh Pavan Kartikeya Bharadwaj Kolluri, Michael Kampouridis, Ravi Shekhar

Automatic speech recognition (ASR) has advanced rapidly in recent years, driven by large-scale pretrained models and end-to-end architectures such as SLAM-ASR. A key component of SLAM-ASR systems is the Whisper speech encoder, which provides robust acoustic representations. While model pruning has been explored for the full Whisper encoder-decoder architecture, its impact within the SLAM-ASR setting remains under-investigated. In this work, we analyze the effects of layer pruning in the Whisper encoder when used as the acoustic backbone of SLAM-ASR. We further examine the extent to which LoRA-based fine-tuning can recover performance degradation caused by pruning. Experiments conducted across three Whisper variants (Small, Medium, Large-v2), three languages representing distinct resource levels (Danish, Dutch, English), and over 200 training runs demonstrate that pruning two encoder layers causes only 2-4% WER degradation, and that combining this pruning with LoRA adaptation consistently outperforms the unpruned baseline while reducing total parameters by 7-14%. Moreover, our error analysis reveals that LoRA primarily compensates through the language model's linguistic priors, reducing total word errors by 11-21% for Dutch and English, with substitutions and deletions showing the largest reductions. However, for low-resource Danish, the reduction is smaller (4-7%), and LoRA introduces increased insertion errors, indicating that compensation effectiveness depends on the LLM's pre-existing language proficiency and available training data.

comment: Accepted at SPEAKABLE Workshop, LREC 2026

☆ An Empirical Recipe for Universal Phone Recognition

Shikhar Bharadwaj, Chin-Jou Li, Kwanghee Choi, Eunjung Yeo, William Chen, Shinji Watanabe, David R. Mortensen

Phone recognition (PR) is a key enabler of multilingual and low-resource speech processing tasks, yet robust performance remains elusive. Highly performant English-focused models do not generalize across languages, while multilingual models underutilize pretrained representations. It also remains unclear how data scale, architecture, and training objective contribute to multilingual PR. We present PhoneticXEUS -- trained on large-scale multilingual data and achieving state-of-the-art performance on both multilingual (17.7% PFER) and accented English speech (10.6% PFER). Through controlled ablations with evaluations across 100+ languages under a unified scheme, we empirically establish our training recipe and quantify the impact of SSL representations, data scale, and loss objectives. In addition, we analyze error patterns across language families, accented speech, and articulatory features. All data and code are released openly.

comment: Submitted to Interspeech 2026. Code: https://github.com/changelinglab/PhoneticXeus

♻ ☆ Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation

Vaibhav Srivastav, Steven Zheng, Eric Bezzam, Eustache Le Bihan, Nithin Rao Koluguri, Piotr Żelasko, Somshubra Majumdar, Adel Moumen, Sanchit Gandhi

We present the Open ASR Leaderboard, a reproducible benchmarking platform with community contributions from academia and industry. It compares 86 open-source and proprietary systems across 12 datasets, with English short- and long-form and multilingual short-form tracks. We standardize word error rate (WER) and inverse real-time factor (RTFx) evaluation for consistent accuracy-efficiency comparisons across model architectures and toolkits (e.g., ESPNet, NeMo, SpeechBrain, Transformers). We observe that Conformer-based encoders paired with transformer-based decoders achieve the best average WER, while connectionist temporal classification (CTC) and token-and-duration transducer (TDT) decoders offer superior RTFx, making them better suited for long-form and batched processing. All code and dataset loaders are open-sourced to support transparent, extensible evaluation. We present our evaluation methodology to facilitate community-driven benchmarking in ASR and other tasks.

comment: Leaderboard: https://huggingface.co/spaces/hf-audio/open_asr_leaderboard ; Code: https://github.com/huggingface/open_asr_leaderboard

♻ ☆ UniLS: End-to-End Audio-Driven Avatars for Unified Listening and Speaking CVPR 2026

Xuangeng Chu, Ruicong Liu, Yifei Huang, Yun Liu, Yichen Peng, Bo Zheng

Generating lifelike conversational avatars requires modeling not just isolated speakers, but the dynamic, reciprocal interaction of speaking and listening. However, modeling the listener is exceptionally challenging: direct audio-driven training fails, producing stiff, static listening motions. This failure stems from a fundamental imbalance: the speaker's motion is strongly driven by speech audio, while the listener's motion primarily follows an internal motion prior and is only loosely guided by external speech. This challenge has led most methods to focus on speak-only generation. The only prior attempt at joint generation relies on extra speaker's motion to produce the listener. This design is not end-to-end, thereby hindering the real-time applicability. To address this limitation, we present UniLS, the first end-to-end framework for generating unified speak-listen expressions, driven by only dual-track audio. Our method introduces a novel two-stage training paradigm. Stage 1 first learns the internal motion prior by training an audio-free autoregressive generator, capturing the spontaneous dynamics of natural facial motion. Stage 2 then introduces the dual-track audio, fine-tuning the generator to modulate the learned motion prior based on external speech cues. Extensive evaluations show UniLS achieves state-of-the-art speaking accuracy. More importantly, it delivers up to 44.1\% improvement in listening metrics, generating significantly more diverse and natural listening expressions. This effectively mitigates the stiffness problem and provides a practical, high-fidelity audio-driven solution for interactive digital humans. Code and demos are available at https://xg-chu.site/project_unils/.

comment: CVPR 2026, code is available at https://github.com/xg-chu/UniLS, more demos are available at https://xg-chu.site/project_unils/

♻ ☆ POTSA: A Cross-Lingual Speech Alignment Framework for Speech-to-Text Translation

Xuanchen Li, Chenrui Cui, Tianrui Wang, Meng Ge, Zikang Huang, Jin Li, Yizhou Peng, Yuheng Lu, Nyima Tashi, Longbiao Wang, Jianwu Dang

♻ ☆ PAVAS: Physics-Aware Video-to-Audio Synthesis

Oh Hyun-Bin, Yuhta Takida, Toshimitsu Uesaka, Tae-Hyun Oh, Yuki Mitsufuji

Recent advances in Video-to-Audio (V2A) generation have achieved impressive perceptual quality and temporal synchronization, yet most models remain appearance-driven, capturing visual-acoustic correlations without considering the physical factors that shape real-world sounds. We present Physics-Aware Video-to-Audio Synthesis (PAVAS), a method that incorporates physical reasoning into a latent diffusion-based V2A generation through the Physics-Driven Audio Adapter (Phy-Adapter). The adapter receives object-level physical parameters estimated by the Physical Parameter Estimator (PPE), which uses a Vision-Language Model (VLM) to infer the moving-object mass and a segmentation-based dynamic 3D reconstruction module to recover its motion trajectory for velocity computation. These physical cues enable the model to synthesize sounds that reflect underlying physical factors. To assess physical realism, we curate VGG-Impact, a benchmark focusing on object-object interactions, and introduce Audio-Physics Correlation Coefficient (APCC), an evaluation metric that measures consistency between physical and auditory attributes. Comprehensive experiments show that PAVAS produces physically plausible and perceptually coherent audio, outperforming existing V2A models in both quantitative and qualitative evaluations. Visit https://physics-aware-video-to-audio-synthesis.github.io for demo videos.

♻ ☆ Listen to Rhythm, Choose Movements: Autoregressive Multimodal Dance Generation via Diffusion and Mamba with Decoupled Dance Dataset

Oran Duan, Yinghua Shen, Yingzhu Lv, Luyang Jie, Yaxin Liu, Qiong Wu

Advances in generative models and sequence learning have greatly promoted research in dance motion generation, yet current methods still suffer from coarse semantic control and poor coherence in long sequences. In this work, we present Listen to Rhythm, Choose Movements (LRCM), a multimodal-guided diffusion framework supporting both diverse input modalities and autoregressive dance motion generation. We explore a feature decoupling paradigm for dance datasets and generalize it to the Motorica Dance dataset, separating motion capture data, audio rhythm, and professionally annotated global and local text descriptions. Our diffusion architecture integrates an audio-latent Conformer and a text-latent Cross-Conformer, and incorporates a Motion Temporal Mamba Module (MTMM) to enable smooth, long-duration autoregressive synthesis. Experimental results indicate that LRCM delivers strong performance in both functional capability and quantitative metrics, demonstrating notable potential in multimodal input scenarios and extended sequence generation. We will release the full codebase, dataset, and pretrained models publicly upon acceptance.

comment: 12 pages, 13 figures

♻ ☆ Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models

Kyudan Jung, Jihwan Kim, Soyoon Kim, Jeonghoon Kim, Jaegul Choo, Cheonbok Park

As the paradigm of AI shifts from text-based LLMs to Speech Language Models (SLMs), there is a growing demand for full-duplex systems capable of real-time, natural human-computer interaction. However, the development of such models is constrained by the scarcity of high-quality, multi-speaker conversational data, as existing large-scale resources are predominantly single-speaker or limited in volume. Addressing the complex dynamics of natural dialogue, such as overlapping and back-channeling remains a challenge, with standard processing pipelines suffering from diarization errors and ASR hallucinations. To bridge this gap, we present a robust and scalable open-source data processing pipeline designed for full-duplex model.

comment: 34 pages, 7 figures, 11 tables

♻ ☆ Nwāchā Munā: A Devanagari Speech Corpus and Proximal Transfer Benchmark for Nepal Bhasha ASR LREC 2026

Rishikesh Kumar Sharma, Safal Narshing Shrestha, Jenny Poudel, Rupak Tiwari, Arju Shrestha, Rupak Raj Ghimire, Bal Krishna Bal

Nepal Bhasha (Newari), an endangered language of the Kathmandu Valley, remains digitally marginalized due to the severe scarcity of annotated speech resources. In this work, we introduce Nwāchā Munā, a newly curated 5.39-hour manually transcribed Devanagari speech corpus for Nepal Bhasha, and establish the first benchmark using script-preserving acoustic modeling. We investigate whether proximal cross-lingual transfer from a geographically and linguistically adjacent language (Nepali) can rival large-scale multilingual pretraining in an ultra-low-resource Automatic Speech Recognition (ASR) setting. Fine-tuning a Nepali Conformer model reduces the Character Error Rate (CER) from a 52.54% zero-shot baseline to 17.59% with data augmentation, effectively matching the performance of the multilingual Whisper-Small model despite utilizing significantly fewer parameters. Our findings demonstrate that proximal transfer from Nepali language serves as a computationally efficient alternative to massive multilingual models. We openly release the dataset and benchmarks to digitally enable the Newari community and foster further research in Nepal Bhasha.

comment: Accepted in CHiPSAL@LREC 2026

Audio and Speech Processing 10

☆ ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining

Anuj Diwan, Eunsol Choi, David Harwath

comment: Under review

☆ Acoustic-to-articulatory Inversion of the Complete Vocal Tract from RT-MRI with Various Audio Embeddings and Dataset Sizes

Sofiane Azzouz, Pierre-André Vuissoz, Yves Laprie

Articulatory-to-acoustic inversion strongly depends on the type of data used. While most previous studies rely on EMA, which is limited by the number of sensors and restricted to accessible articulators, we propose an approach aiming at a complete inversion of the vocal tract, from the glottis to the lips. To this end, we used approximately 3.5 hours of RT-MRI data from a single speaker. The innovation of our approach lies in the use of articulator contours automatically extracted from MRI images, rather than relying on the raw images themselves. By focusing on these contours, the model prioritizes the essential geometric dynamics of the vocal tract while discarding redundant pixel-level information. These contours, alongside denoised audio, were then processed using a Bi-LSTM architecture. Two experiments were conducted: (1) the analysis of the impact of the audio embedding, for which three types of embeddings were evaluated as input to the model (MFCCs, LCCs, and HuBERT), and (2) the study of the influence of the dataset size, which we varied from 10 minutes to 3.5 hours. Evaluation was performed on the test data using RMSE, median error, as well as Tract Variables, to which we added an additional measurement: the larynx height. The average RMSE obtained is 1.48\,mm, compared with the pixel size (1.62\,mm). These results confirm the feasibility of a complete vocal-tract inversion using RT-MRI data.

☆ Can Hierarchical Cross-Modal Fusion Predict Human Perception of AI Dubbed Content? ICASSP 2026

Ashwini Dasare, Nirmesh Shah, Ashishkumar Gudmalwar, Pankaj Wasnik

Evaluating AI generated dubbed content is inherently multi-dimensional, shaped by synchronization, intelligibility, speaker consistency, emotional alignment, and semantic context. Human Mean Opinion Scores (MOS) remain the gold standard but are costly and impractical at scale. We present a hierarchical multimodal architecture for perceptually meaningful dubbing evaluation, integrating complementary cues from audio, video, and text. The model captures fine-grained features such as speaker identity, prosody, and content from audio, facial expressions and scene-level cues from video and semantic context from text, which are progressively fused through intra and inter-modal layers. Lightweight LoRA adapters enable parameter-efficient fine-tuning across modalities. To overcome limited subjective labels, we derive proxy MOS by aggregating objective metrics with weights optimized via active learning. The proposed architecture was trained on 12k Hindi-English bidirectional dubbed clips, followed by fine-tuning with human MOS. Our approach achieves strong perceptual alignment (PCC > 0.75), providing a scalable solution for automatic evaluation of AI-dubbed content.

comment: Accepted at ICASSP 2026

☆ VAANI: Capturing the language landscape for an inclusive digital India

Sujith Pulikodan, Abhayjeet Singh, Agneedh Basu, Lokesh Rady, Nihar Desai, Pavan Kumar J, Prajjwal Srivastav, Pranav D Bhat, Raghu Dharmaraju, Ritika Gupta, Sathvik Udupa, Saurabh Kumar, Sumit Sharma, Vaibhav Vishwakarma, Visruth Sanka, Dinesh Tewari, Harsh Dhand, Amrita Kamat, Sukhwinder Singh, Shikhar Vashishth, Partha Talukdar, Raj Acharya, Prasanta Kumar Ghosh

☆ BiFormer3D: Grid-Free Time-Domain Reconstruction of Head-Related Impulse Responses with a Spatially Encoded Transformer

Shaoheng Xu, Chunyi Sun, Jihui Zhang, Amy Bastine, Prasanga N. Samarasinghe, Thushara D. Abhayapala, Hongdong Li

Individualized head-related impulse responses (HRIRs) enable binaural rendering, but dense per-listener measurements are costly. We address HRIR spatial up-sampling from sparse per-listener measurements: given a few measured HRIRs for a listener, predict HRIRs at unmeasured target directions. Prior learning methods often work in the frequency domain, rely on minimum-phase assumptions or separate timing models, and use a fixed direction grid, which can degrade temporal fidelity and spatial continuity. We propose BiFormer3D, a time-domain, grid-free binaural Transformer for reconstructing HRIRs at arbitrary directions from sparse inputs. It uses sinusoidal spatial features, a Conv1D refinement module, and auxiliary interaural time difference (ITD) and interaural level difference (ILD) heads. On SONICOM, it improves normalized mean squared error (NMSE), cosine distance, and ITD/ILD errors over prior methods; ablations validate modules and show minimum-phase pre-processing is unnecessary.

comment: The paper was submitted for review to Interspeech 2026

☆ An Empirical Recipe for Universal Phone Recognition

Shikhar Bharadwaj, Chin-Jou Li, Kwanghee Choi, Eunjung Yeo, William Chen, Shinji Watanabe, David R. Mortensen

comment: Submitted to Interspeech 2026. Code: https://github.com/changelinglab/PhoneticXeus

♻ ☆ Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation

Vaibhav Srivastav, Steven Zheng, Eric Bezzam, Eustache Le Bihan, Nithin Rao Koluguri, Piotr Żelasko, Somshubra Majumdar, Adel Moumen, Sanchit Gandhi

comment: Leaderboard: https://huggingface.co/spaces/hf-audio/open_asr_leaderboard ; Code: https://github.com/huggingface/open_asr_leaderboard

♻ ☆ Joint Optimization of Speaker and Spoof Detectors for Spoofing-Robust Automatic Speaker Verification

Oğuzhan Kurnaz, Jagabandhu Mishra, Tomi H. Kinnunen, Cemal Hanilçi

Spoofing-robust speaker verification (SASV) combines the tasks of speaker and spoof detection to authenticate speakers under adversarial settings. Many SASV systems rely on fusion of speaker and spoof cues at embedding, score or decision levels, based on independently trained subsystems. In this study, we respect similar modularity of the two subsystems, by integrating their outputs using trainable back-end classifiers. In particular, we explore various approaches for directly optimizing the back-end for the recently-proposed SASV performance metric (a-DCF) as a training objective. Our experiments on the ASVspoof 5 dataset demonstrate two important findings: (i) nonlinear score fusion consistently improves a-DCF over linear fusion, and (ii) the combination of weighted cosine scoring for speaker detection with SSL-AASIST for spoof detection achieves state-of-the-art performance, reducing min a-DCF to 0.196 and SPF-EER to 7.6%. These contributions highlight the importance of modular design, calibrated integration, and task-aligned optimization for advancing robust and interpretable SASV systems.

comment: submitted to IEEE/ACM Transactions on Audio, Speech and Language Processing

♻ ☆ X-OPD: Cross-Modal On-Policy Distillation for Capability Alignment in Speech LLMs

Di Cao, Dongjie Fu, Hai Yu, Siqi Zheng, Xu Tan, Tao Jin

While the shift from cascaded dialogue systems to end-to-end (E2E) speech Large Language Models (LLMs) improves latency and paralinguistic modeling, E2E models often exhibit a significant performance degradation compared to their text-based counterparts. The standard Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) training methods fail to close this gap. To address this, we propose X-OPD, a novel Cross-Modal On-Policy Distillation framework designed to systematically align the capabilities of Speech LLMs to their text-based counterparts. X-OPD enables the Speech LLM to explore its own distribution via on-policy rollouts, where a text-based teacher model evaluates these trajectories and provides token-level feedback, effectively distilling teacher's capabilities into student's multi-modal representations. Extensive experiments across multiple benchmarks demonstrate that X-OPD significantly narrows the gap in complex tasks while preserving the model's inherent capabilities.

comment: Submitted to Interspeech 2026

♻ ☆ Sommelier: Scalable Open Multi-turn Audio Pre-processing for Full-duplex Speech Language Models

Kyudan Jung, Jihwan Kim, Soyoon Kim, Jeonghoon Kim, Jaegul Choo, Cheonbok Park

comment: 34 pages, 7 figures, 11 tables

2026-03-29

Sound 6

☆ HumMusQA: A Human-written Music Understanding QA Benchmark Dataset

Benno Weck, Pablo Puentes, Andrea Poltronieri, Satyajeet Prabhu, Dmitry Bogdanov

The evaluation of music understanding in Large Audio-Language Models (LALMs) requires a rigorously defined benchmark that truly tests whether models can perceive and interpret music, a standard that current data methodologies frequently fail to meet. This paper introduces a meticulously structured approach to music evaluation, proposing a new dataset of 320 hand-written questions curated and validated by experts with musical training, arguing that such focused, manual curation is superior for probing complex audio comprehension. To demonstrate the use of the dataset, we benchmark six state-of-the-art LALMs and additionally test their robustness to uni-modal shortcuts.

comment: Dataset available at https://doi.org/10.5281/zenodo.18462523

☆ EvA: An Evidence-First Audio Understanding Paradigm for LALMs

Xinyuan Xie, Shunian Chen, Zhiheng Liu, Yuhao Zhang, Zhiqiang Lv, Liyin Liang, Benyou Wang

Large Audio Language Models (LALMs) still struggle in complex acoustic scenes because they often fail to preserve task-relevant acoustic evidence before reasoning begins. We call this failure the evidence bottleneck: state-of-the-art systems show larger deficits in evidence extraction than in downstream reasoning, suggesting that the main limitation lies in upstream perception rather than reasoning policy. To address this problem, we propose EvA (Evidence-First Audio), a dual-path architecture that combines Whisper and CED-Base through non-compressive, time-aligned fusion. EvA first aggregates intermediate CED layers to preserve multi-scale acoustic cues, then aligns the aggregated CED features to the Whisper timeline and adds the two streams without changing sequence length. We also build EvA-Perception, a large-scale open-source training set with about 54K event-ordered captions (150 h) and about 500K QA pairs. Under a unified zero-shot protocol, EvA achieves the best open-source Perception scores on MMAU, MMAR, and MMSU, and improves over Kimi-Audio-7B on all reported metrics, with the largest gains on perception-heavy splits. These results support the evidence-first hypothesis: stronger audio understanding depends on preserving acoustic evidence before reasoning.

☆ A General Model for Deepfake Speech Detection: Diverse Bonafide Resources or Diverse AI-Based Generators

Lam Pham, Khoi Vu, Dat Tran, David Fischinger, Simon Freitter, Marcel Hasenbalg, Davide Antonutti, Alexander Schindler, Martin Boyer, Ian McLoughlin

In this paper, we analyze two main factors of Bonafide Resource (BR) or AI-based Generator (AG) which affect the performance and the generality of a Deepfake Speech Detection (DSD) model. To this end, we first propose a deep-learning based model, referred to as the baseline. Then, we conducted experiments on the baseline by which we indicate how Bonafide Resource (BR) and AI-based Generator (AG) factors affect the threshold score used to detect fake or bonafide input audio in the inference process. Given the experimental results, a dataset, which re-uses public Deepfake Speech Detection (DSD) datasets and shows a balance between Bonafide Resource (BR) or AI-based Generator (AG), is proposed. We then train various deep-learning based models on the proposed dataset and conduct cross-dataset evaluation on different benchmark datasets. The cross-dataset evaluation results prove that the balance of Bonafide Resources (BR) and AI-based Generators (AG) is the key factor to train and achieve a general Deepfake Speech Detection (DSD) model.

☆ Advancing Multi-Instrument Music Transcription: Results from the 2025 AMT Challenge NeurIPS 2025

Ojas Chaturvedi, Kayshav Bhardwaj, Tanay Gondil, Benjamin Shiue-Hal Chou, Kristen Yeon-Ji Yun, Yung-Hsiang Lu, Yujia Yan, Sungkyun Chang

This paper presents the results of the 2025 Automatic Music Transcription (AMT) Challenge, an online competition to benchmark progress in multi-instrument transcription. Eight teams submitted valid solutions; two outperformed the baseline MT3 model. The results highlight both advances in transcription accuracy and the remaining difficulties in handling polyphony and timbre variation. We conclude with directions for future challenges: broader genre coverage and stronger emphasis on instrument detection.

comment: 7 pages, 3 figures. Accepted to the AI for Music Workshop at NeurIPS 2025

☆ Investigation on the Robustness of Acoustic Foundation Models on Post Exercise Speech

Xiangyuan Xue, Yuyu Wang, Ruijie Yao, Xiaoyue Ni, Xiaofan Jiang, Jingping Nie

Automatic speech recognition (ASR) has been extensively studied on neutral and stationary speech, yet its robustness under post-exercise physiological shift remains underexplored. Compared with resting speech, post-exercise speech often contains micro-breaths, non-semantic pauses, unstable phonation, and repetitions caused by reduced breath support, making transcription more difficult. In this work, we benchmark acoustic foundation models on post-exercise speech under a unified evaluation protocol. We compare sequence-to-sequence models (Whisper and FunASR/Paraformer) and self-supervised encoders with CTC decoding (Wav2Vec2, HuBERT, and WavLM), under both off-the-shelf inference and post-exercise in-domain fine-tuning. Across the Static/Post-All benchmark, most models degrade on post-exercise speech, while FunASR shows the strongest baseline robustness at 14.57% WER and 8.21% CER on Post-All. Fine-tuning substantially improves several CTC-based models, whereas Whisper shows unstable adaptation. As an exploratory case study, we further stratify results by fluent and non-fluent speakers; although the non-fluent subset is small, it is consistently more challenging than the fluent subset. Overall, our findings show that post-exercise ASR robustness is strongly model-dependent, that in-domain adaptation can be highly effective but not uniformly stable, and that future post-exercise ASR studies should explicitly separate fluency-related effects from exercise-induced speech variation.

♻ ☆ Foundation Models for Bioacoustics -- a Comparative Review

Raphael Schwinger, Paria Vali Zadeh, Lukas Rauch, Mats Kurz, Tom Hauschild, Sam Lapp, Sven Tomforde

Automated bioacoustic analysis is essential for biodiversity monitoring and conservation, requiring advanced deep learning models that can adapt to diverse bioacoustic tasks. This article presents a comprehensive review of large-scale pretrained bioacoustic foundation models and systematically investigates their transferability across multiple bioacoustic classification tasks. We overview bioacoustic representation learning by analysing pretraining data sources and benchmarks. On this basis, we review bioacoustic foundation models, dissecting the models' training data, preprocessing, augmentations, architecture, and training paradigm. Additionally, we conduct an extensive empirical study of selected models on the BEANS and BirdSet benchmarks, evaluating generalisability under linear and attentive probing. Our experimental analysis reveals that Perch~2.0 achieves the highest BirdSet score (restricted evaluation) and the strongest linear probing result on BEANS, building on diverse multi-taxa supervised pretraining; that BirdMAE is the best model among probing-based strategies on BirdSet and second on BEANS after BEATs$_{NLM}$, the encoder of NatureLM-audio; that attentive probing is beneficial to extract the full performance of transformer-based models; and that general-purpose audio models trained with self-supervised learning on AudioSet outperform many specialised bird sound models on BEANS when evaluated with attentive probing. These findings provide valuable guidance for practitioners selecting appropriate models to adapt them to new bioacoustic classification tasks via probing.

comment: Preprint

Audio and Speech Processing 1

♻ ☆ Foundation Models for Bioacoustics -- a Comparative Review

Raphael Schwinger, Paria Vali Zadeh, Lukas Rauch, Mats Kurz, Tom Hauschild, Sam Lapp, Sven Tomforde

comment: Preprint

2026-03-28

Sound 6

☆ SHroom: A Python Framework for Ambisonics Room Acoustics Simulation and Binaural Rendering

Yhonatan Gayer

Spherical Harmonics ROOM), an open-source Python library for room acoustics simulation using Ambisonics, available at https://github.com/Yhonatangayer/shroom and installable via \texttt{pip install pyshroom}. \textbf{shroom} projects image-source contributions onto a Spherical Harmonics (SH) basis, yielding a composable pipeline for binaural decoding, spherical array simulation, and real-time head rotation. Benchmarked against \texttt{pyroomacoustics} with an $N=30$ reference, \textbf{shroom} with Magnitude Least Squares (MagLS) achieves perceptual transparency (2.02~dB Log Spectral Distance (LSD) at $N=5$, within the 1--2~dB Just Noticeable Difference (JND)) while its fixed-once decode amortises over multiple sources ($K=1$-to-$8$: slowdown narrows from $7\times$ to $3.1\times$). For dynamic head rotation, \textbf{shroom} applies a Wigner-D multiply at $<1$~ms/frame, making it the only architecturally viable real-time choice.

☆ TokenDance: Token-to-Token Music-to-Dance Generation with Bidirectional Mamba CVPR2026

Ziyue Yang, Kaixing Yang, Xulong Tang

Music-to-dance generation has broad applications in virtual reality, dance education, and digital character animation. However, the limited coverage of existing 3D dance datasets confines current models to a narrow subset of music styles and choreographic patterns, resulting in poor generalization to real-world music. Consequently, generated dances often become overly simplistic and repetitive, substantially degrading expressiveness and realism. To tackle this problem, we present TokenDance, a two-stage music-to-dance generation framework that explicitly addresses this limitation through dual-modality tokenization and efficient token-level generation. In the first stage, we discretize both dance and music using Finite Scalar Quantization, where dance motions are factorized into upper and lower-body components with kinematic-dynamic constraints, and music is decomposed into semantic and acoustic features with dedicated codebooks to capture choreography-specific structures. In the second stage, we introduce a Local-Global-Local token-to-token generator built on a Bidirectional Mamba backbone, enabling coherent motion synthesis, strong music-dance alignment, and efficient non-autoregressive inference. Extensive experiments demonstrate that TokenDance achieves overall state-of-the-art (SOTA) performance in both generation quality and inference speed, highlighting its effectiveness and practical value for real-world music-to-dance applications.

comment: CVPR2026 Workshop on HuMoGen

☆ Can pre-trained Deep Learning models predict groove ratings?

Axel Marmoret, Nicolas Farrugia, Jan Alexander Stupacher

This study explores the extent to which deep learning models can predict groove and its related perceptual dimensions directly from audio signals. We critically examine the effectiveness of seven state-of-the-art deep learning models in predicting groove ratings and responses to groove-related queries through the extraction of audio embeddings. Additionally, we compare these predictions with traditional handcrafted audio features. To better understand the underlying mechanics, we extend this methodology to analyze predictions based on source-separated instruments, thereby isolating the contributions of individual musical elements. Our analysis reveals a clear separation of groove characteristics driven by the underlying musical style of the tracks (funk, pop, and rock). These findings indicate that deep audio representations can successfully encode complex, style-dependent groove components that traditional features often miss. Ultimately, this work highlights the capacity of advanced deep learning models to capture the multifaceted concept of groove, demonstrating the strong potential of representation learning to advance predictive Music Information Retrieval methodologies.

comment: Submitted to the SMC 2026 conference. 3 figures and 2 tables

☆ Unsupervised Evaluation of Deep Audio Embeddings for Music Structure Analysis

Axel Marmoret

Music Structure Analysis (MSA) aims to uncover the high-level organization of musical pieces. State-of-the-art methods are often based on supervised deep learning, but these methods are bottlenecked by the need for heavily annotated data and inherent structural ambiguities. In this paper, we propose an unsupervised evaluation of nine open-source, generic pre-trained deep audio models, on MSA. For each model, we extract barwise embeddings and segment them using three unsupervised segmentation algorithms (Foote's checkerboard kernels, spectral clustering, and Correlation Block-Matching (CBM)), focusing exclusively on boundary retrieval. Our results demonstrate that modern, generic deep embeddings generally outperform traditional spectrogram-based baselines, but not systematically. Furthermore, our unsupervised boundary estimation methodology generally yields stronger performance than recent linear probing baselines. Among the evaluated techniques, the CBM algorithm consistently emerges as the most effective downstream segmentation method. Finally, we highlight the artificial inflation of standard evaluation metrics and advocate for the systematic adoption of ``trimming'', or even ``double trimming'' annotations to establish more rigorous MSA evaluation standards.

comment: Submitted to the SMC 2026 conference. 2 figures and 2 tables in the main document, 7 figures in Appendix

☆ Two-Stage Acoustic Adaptation with Gated Cross-Attention Adapters for LLM-Based Multi-Talker Speech Recognition

Hao Shi, Yuan Gao, Xugang Lu, Tatsuya Kawahara

Large Language Models (LLMs) are strong decoders for Serialized Output Training (SOT) in two-talker Automatic Speech Recognition (ASR), yet their performance degrades substantially in challenging conditions such as three-talker mixtures. A key limitation is that current systems inject acoustic evidence only through a projected prefix, which can be lossy and imperfectly aligned with the LLM input space, providing insufficient fine-grained grounding during decoding. Addressing this limitation is crucial for robust multi-talker ASR, especially in three-talker mixtures. This paper improves LLM-based multi-talker ASR by explicitly injecting talker-aware acoustic evidence into the decoder. We first revisit Connectionist Temporal Classification (CTC)-derived prefix prompting and compare three variants with increasing acoustic content. The CTC information is obtained using the serialized CTC proposed in our previous works. While acoustic-enriched prompts outperform the SOT-only baseline, prefix-only conditioning remains inadequate for three-talker mixtures. We therefore propose a lightweight gated residual cross-attention adapter and design a two-stage acoustic adaptation framework based on low-rank updates (LoRA). In Stage 1, we insert gated cross-attention adapters after the self-attention sub-layer to stably inject acoustic embeddings as external memory. In Stage 2, we refine both the cross-attention adapters and the pretrained LLM's self-attention projections using parameter-efficient LoRA, improving robustness for large backbones under limited data; the learned updates are merged into the base weights for inference. Experiments on Libri2Mix/Libri3Mix under clean and noisy conditions show consistent gains, with particularly large improvements in three-talker settings.

♻ ☆ Enhancing Automatic Chord Recognition via Pseudo-Labeling and Knowledge Distillation

Nghia Phan, Rong Jin, Gang Liu, Xiao Dong

Automatic Chord Recognition (ACR) is constrained by the scarcity of aligned chord labels, as well-aligned annotations are costly to acquire. At the same time, open-weight pre-trained models are currently more accessible than their proprietary training data. In this work, we present a two-stage training pipeline that leverages pre-trained models together with unlabeled audio. The proposed method decouples training into two stages. In the first stage, we use a pre-trained BTC model as a teacher to generate pseudo-labels for over 1,000 hours of diverse unlabeled audio and train a student model solely on these pseudo-labels. In the second stage, the student is continually trained on ground-truth labels as they become available. To prevent catastrophic forgetting of the representations learned in the first stage, we apply selective knowledge distillation (KD) from the teacher as a regularizer. In our experiments, two models (BTC, 2E1D) were used as students. In stage 1, using only pseudo-labels, the BTC student achieves over 99% of the teacher's performance, while the 2E1D model achieves about 97% across seven standard mir_eval metrics. After a single training run for both students in stage 2, the resulting BTC student model surpasses the traditional supervised learning baseline by 2.5% and the original pre-trained teacher model by 1.1-3.2% across all metrics. The resulting 2E1D student model improves over the traditional supervised learning baseline by 2.67% on average and achieves almost the same performance as the teacher. Both cases show large gains on rare chord qualities.

comment: 8 pages, 6 figures, 3 tables

Audio and Speech Processing 2

☆ SHroom: A Python Framework for Ambisonics Room Acoustics Simulation and Binaural Rendering

Yhonatan Gayer

☆ Can pre-trained Deep Learning models predict groove ratings?

Axel Marmoret, Nicolas Farrugia, Jan Alexander Stupacher

comment: Submitted to the SMC 2026 conference. 3 figures and 2 tables

2026-03-27

Sound 21

☆ Diachronic Modeling of Tonal Coherence on the Tonnetz Across Classical and Popular Repertoires

Weilun Xu, Edward Hall, Martin Rohrmeier

How do different musical traditions achieve tonal coherence? Most computational measures to date have analysed tonal coherence in terms of a single dimension, whereas a multi-dimensional analyses have not been sufficiently explored. We propose a new model drawing on the concept of the Tonnetz -- we define two partially independent measures: \emph{tonal focus}, the concentration of pitch content near a tonal center; and \emph{tonal connection}, the degree to which pitch content reflects structured intervallic pathways back to that center. Analyzing over 2,800 pieces from Western classical and popular traditions, we find that these traditions occupy overlapping yet distinguishable regions of the two-dimensional space. Popular music shows higher tonal focus, while classical music exhibits higher tonal connection. Our complementary measures ground the differences between different tonal styles in quantitative evidence, and offer interpretable dimensions for computational music analysis and controllable generation.

☆ Algo Pärt: An Algorithmic Reconstruction of Arvo Pärt's Summa

Bas Cornelissen

Arvo Pärt is one of the most popular contemporary composers, known for his highly original tintinnabuli style. Works in this style are typically composed according to precise procedures and have even been described as algorithmic compositions. To understand how algorithmic Pärt's music exactly is, this paper presents an analysis by synthesis: it proposes an algorithm that almost completely reconstructs the score of Summa, his "most strictly constructed and most encrypted work," according to Pärt himself in 1994. The piece is analyzed and then formalized using so-called tintinnabuli processes. An implementation of the resulting algorithm generates a musical score matching Summa in over 93% of the notes. Due to interdependencies between the voices, only half of the mistakes (3.5%) need to be corrected to reproduce the original score faithfully. This study shows that Summa is a largely algorithmic composition and offers new perspectives on the music of Arvo Pärt.

comment: 21 pages, 15 figures

☆ Rhythmic segment analysis: Conceptualizing, visualizing, and measuring rhythmic data

Bas Cornelissen

This paper develops a framework for conceptualizing, visualizing, and measuring regularities in rhythmic data. I propose to think about rhythmic data in terms of interval segments: fixed-length groups of consecutive intervals, which can be decomposed into a duration and a pattern (the ratios between the intervals). This simple conceptual framework unifies three rhythmic visualization methods and yields a fourth: the pattern-duration plot. When paired with a cluster transition network, it intuitively reveals regularities in both synthetic and real-world rhythmic data. Moreover, the framework generalizes two common measures of rhythmic structure: rhythm ratios and the normalized pairwise variability index (nPVI). In particular, nPVI can be reconstructed as the average distance from isochrony, and I propose a more general measure of anisochrony to replace it. Finally, the novel concept of quantality may shed light on wider debates regarding small-integer-ratio rhythms.

comment: 15 pages, 7 figures

☆ Multilingual Stutter Event Detection for English, German, and Mandarin Speech

Felix Haas, Sebastian P. Bayerl

This paper presents a multi-label stuttering detection system trained on multi-corpus, multilingual data in English, German, and Mandarin.By leveraging annotated stuttering data from three languages and four corpora, the model captures language-independent characteristics of stuttering, enabling robust detection across linguistic contexts. Experimental results demonstrate that multilingual training achieves performance comparable to and, in some cases, even exceeds that of previous systems. These findings suggest that stuttering exhibits cross-linguistic consistency, which supports the development of language-agnostic detection systems. Our work demonstrates the feasibility and advantages of using multilingual data to improve generalizability and reliability in automated stuttering detection.

☆ Probabilistic Multilabel Graphical Modelling of Motif Transformations in Symbolic Music

Ron Taieb, Yoel Greenberg, Barak Sober

Motifs often recur in musical works in altered forms, preserving aspects of their identity while undergoing local variation. This paper investigates how such motivic transformations occur within their musical context in symbolic music. To support this analysis, we develop a probabilistic framework for modeling motivic transformations and apply it to Beethoven's piano sonatas by integrating multiple datasets that provide melodic, rhythmic, harmonic, and motivic information within a unified analytical representation. Motif transformations are represented as multilabel variables by comparing each motif instance to a designated reference occurrence within its local context, ensuring consistent labeling across transformation families. We introduce a multilabel Conditional Random Field to model how motif-level musical features influence the occurrence of transformations and how different transformation families tend to co-occur. Our goal is to provide an interpretable, distributional analysis of motivic transformation patterns, enabling the study of their structural relationships and stylistic variation. By linking computational modeling with music-theoretical interpretation, the proposed framework supports quantitative investigation of musical structure and complexity in symbolic corpora and may facilitate the analysis of broader compositional patterns and writing practices.

comment: 23 pages (21 pages main text), 2 figures. Submitted to Journal of New Music Research (Special Issue on Computational and Cognitive Musicology)

☆ AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection

Hai-Son Nguyen-Le, Hung-Cuong Nguyen-Thanh, Nhien-An Le-Khac, Dinh-Thuc Nguyen, Hong-Hanh Nguyen-Le

The rapid advancement of generative models has enabled highly realistic audio deepfakes, yet current detectors suffer from a critical bias problem, leading to poor generalization across unseen datasets. This paper proposes Artifact-Focused Self-Synthesis (AFSS), a method designed to mitigate this bias by generating pseudo-fake samples from real audio via two mechanisms: self-conversion and self-reconstruction. The core insight of AFSS lies in enforcing same-speaker constraints, ensuring that real and pseudo-fake samples share identical speaker identity and semantic content. This forces the detector to focus exclusively on generation artifacts rather than irrelevant confounding factors. Furthermore, we introduce a learnable reweighting loss to dynamically emphasize synthetic samples during training. Extensive experiments across 7 datasets demonstrate that AFSS achieves state-of-the-art performance with an average EER of 5.45\%, including a significant reduction to 1.23\% on WaveFake and 2.70\% on In-the-Wild, all while eliminating the dependency on pre-collected fake datasets. Our code is publicly available at https://github.com/NguyenLeHaiSonGit/AFSS.

comment: Accepted at International Joint Conference on Neural Networks 2026

☆ CA-TCN: A Causal-Anticausal Temporal Convolutional Network for Direct Auditory Attention Decoding

Iñigo García-Ugarte, Rubén Eguinoa, Ricardo San Martín, Daniel Paternain, Carmen Vidaurre

A promising approach for steering auditory attention in complex listening environments relies on Auditory Attention Decoding (AAD), which aim to identify the attended speech stream in a multiple speaker scenario from neural recordings. Entrainment-based AAD approaches, typically assume access to clean speech sources and electroencephalography (EEG) signals to exploit low-frequency correlations between the neural response and the attended stimulus. In this study, we propose CA-TCN, a Causal-Anticausal Temporal Convolutional Network that directly classifies the attended speaker. The proposed architecture integrates several best practices from convolutional neural networks in sequence processing tasks. Importantly, it explicitly aligns auditory stimuli and neural responses by employing separate causal and anticausal convolutions respectively, with distinct receptive fields operating in opposite temporal directions. Experimental results, obtained through comparisons with three baseline AAD models, demonstrated that CA-TCN consistently improved decoding accuracy across datasets and decision windows, with gains ranging from 0.5% to 3.2% for subject-independent models and from 0.8% to 2.9% for subject-specific models compared with the next best-performing model, AADNet. Moreover, these improvements were statistically significant in four of the six evaluated settings when comparing Minimum Expected Switch Duration distributions. Beyond accuracy, the model demonstrated spatial robustness across different conditions, as the EEG spatial filters exhibited stable patterns across datasets. Overall, this work introduces an accurate and unified AAD model that outperforms existing methods while considering practical benefits for online processing scenarios. These findings contribute to advancing the state of AAD and its applicability in real-world systems.

☆ LLaDA-TTS: Unifying Speech Synthesis and Zero-Shot Editing via Masked Diffusion Modeling

Xiaoyu Fan, Huizhi Xie, Wei Zou, Yunzhang Chen

Large language model (LLM)-based text-to-speech (TTS) systems achieve remarkable naturalness via autoregressive (AR) decoding, but require N sequential steps to generate N speech tokens. We present LLaDA-TTS, which replaces the AR LLM with a masked diffusion model that completes generation in a fixed number of parallel steps, decoupling inference latency from sequence length. Remarkably, using only 50 hours of fine-tuning data, we successfully transfer a pretrained AR checkpoint to the masked diffusion paradigm via bidirectional attention. At 64 steps, LLaDA-TTS achieves 0.98% CER (zh) and 1.96% WER (en) on Seed-TTS-Eval, matching the original CosyVoice 3 baseline performance while delivering a 2x LLM-stage speedup--a notable acceleration achieved despite the absence of KV cache, an optimization the AR baseline heavily relies on. Beyond acceleration, the bidirectional architecture naturally enables zero-shot speech editing--including word-level insertion, deletion, and substitution--without any additional training. Theoretically, we prove that AR-pretrained weights are near-optimal for bidirectional masked prediction under the locality property of acoustic tokens, explaining this rapid convergence. This general method modifies only the attention mask and objective, applying seamlessly to any LLM-based AR TTS system. Code and audio samples will be available at https://deft-piroshki-b652b5.netlify.app/.

comment: 11 pages, 6 figures, 2 tables

☆ A Power-Weighted Noncentral Complex Gaussian Distribution

Toru Nakashika

The complex Gaussian distribution has been widely used as a fundamental spectral and noise model in signal processing and communication. However, its Gaussian structure often limits its ability to represent the diverse amplitude characteristics observed in individual source signals. On the other hand, many existing non-Gaussian amplitude distributions derived from hyperspherical models achieve good empirical fit due to their power-law structures, while they do not explicitly account for the complex-plane geometry inherent in complex-valued observations. In this paper, we propose a new probabilistic model for complex-valued random variables, which can be interpreted as a power-weighted noncentral complex Gaussian distribution. Unlike conventional hyperspherical amplitude models, the proposed model is formulated directly on the complex plane and preserves the geometric structure of complex-valued observations while retaining a higher-dimensional interpretation. The model introduces a nonlinear phase diffusion through a single shape parameter, enabling continuous control of the distributional geometry from arc-shaped diffusion along the phase direction to concentration of probability mass toward the origin. We formulate the proposed distribution and analyze the statistical properties of the induced amplitude distribution. The derived amplitude and power distributions provide a unified framework encompassing several widely used distributions in signal modeling, including the Rice, Nakagami, and gamma distributions. Experimental results on speech power spectra demonstrate that the proposed model consistently outperforms conventional distributions in terms of log-likelihood.

☆ Cinematic Audio Source Separation Using Visual Cues CVPR 2026

Kang Zhang, Suyeon Lee, Arda Senocak, Joon Son Chung

Cinematic Audio Source Separation (CASS) aims to decompose mixed film audio into speech, music, and sound effects, enabling applications like dubbing and remastering. Existing CASS approaches are audio-only, overlooking the inherent audio-visual nature of films, where sounds often align with visual cues. We present the first framework for audio-visual CASS (AV-CASS), leveraging visual context to enhance separation quality. Our method formulates CASS as a conditional generative modeling problem using conditional flow matching, enabling multimodal audio source separation. To address the lack of cinematic datasets with isolated sound tracks, we introduce a training data synthesis pipeline that pairs in-the-wild audio and video streams (e.g., facial videos for speech, scene videos for effects) and design a dedicated visual encoder for this dual-stream setup. Trained entirely on synthetic data, our model generalizes effectively to real-world cinematic content and achieves strong performance on synthetic, real-world, and audio-only CASS benchmarks. Code and demo are available at \url{https://cass-flowmatching.github.io}.

comment: CVPR 2026. Project page: https://cass-flowmatching.github.io

☆ A Human-Inspired Decoupled Architecture for Efficient Audio Representation Learning

Harunori Kawano, Takeshi Sasaki

While self-supervised learning (SSL) has revolutionized audio representation, the excessive parameterization and quadratic computational cost of standard Transformers limit their deployment on resource-constrained devices. To address this bottleneck, we propose HEAR (Human-inspired Efficient Audio Representation), a novel decoupled architecture. Inspired by the human cognitive ability to isolate local acoustic features from global context, HEAR splits the processing pipeline into two dedicated modules: an Acoustic Model for local feature extraction and a Task Model for global semantic integration. Coupled with an Acoustic Tokenizer trained via knowledge distillation, our approach enables robust Masked Audio Modeling (MAM). Extensive experiments demonstrate that HEAR requires only 15M parameters and 9.47 GFLOPs for inference, operating at a fraction of the computational cost of conventional foundation models (which typically require 85M-94M parameters). Despite this high efficiency, HEAR achieves highly competitive performance across diverse audio classification benchmarks. The code and pre-trained models are available at https://github.com/HarunoriKawano/HEAR

♻ ☆ Acoustic Overspecification in Electronic Dance Music Taxonomy

Weilun Xu, Tianhao Dai, Oscar Goudet, Xiaoxuan Wang

Electronic Dance Music (EDM) classification typically relies on industry-defined taxonomies, with current supervised approaches naturally assuming the validity of prescribed subgenre labels. However, whether these commercial distinctions reflect genuine acoustic differences remains largely unexplored. In this paper, we propose an unsupervised approach to discover the natural acoustic structure of EDM independent of commercial labels. To address the historical lack of EDM-specific feature design in MIR, we systematically construct a tailored, interpretable acoustic feature space capturing the genre's defining production techniques, spectral textures, and layered rhythmic patterns. To ensure our findings reflect inherent acoustic structure rather than feature engineering artifacts, we validate our clustering against state-of-the-art pre-trained audio embeddings (MERT and CLAP). Across both our bespoke feature space and the pre-trained embeddings, clustering consistently identifies 20 or fewer natural acoustic families -- suggesting current commercial EDM taxonomy is acoustically overspecified by nearly one-half.

♻ ☆ DiffAU: Diffusion-Based Ambisonics Upscaling

Amit Milstein, Nir Shlezinger, Boaz Rafaely

Spatial audio enhances immersion by reproducing 3D sound fields, with Ambisonics offering a scalable format for this purpose. While first-order Ambisonics (FOA) notably facilitates hardware-efficient acquisition and storage of sound fields as compared to high-order Ambisonics (HOA), its low spatial resolution limits realism, highlighting the need for Ambisonics upscaling (AU) as an approach for increasing the order of Ambisonics signals. In this work we propose DiffAU, a cascaded AU method that leverages recent developments in diffusion models combined with novel adaptation to spatial audio to generate 3rd order Ambisonics from FOA. By learning data distributions, DiffAU provides a principled approach that rapidly and reliably reproduces HOA in various settings. Experiments in anechoic conditions with multiple speakers, show strong objective and perceptual performance.

♻ ☆ Does Audio Deepfake Detection Generalize?

Nicolas M. Müller, Pavel Czempin, Franziska Dieckmann, Adam Froghyar, Konstantin Böttinger

Current text-to-speech algorithms produce realistic fakes of human voices, making deepfake detection a much-needed area of research. While researchers have presented various techniques for detecting audio spoofs, it is often unclear exactly why these architectures are successful: Preprocessing steps, hyperparameter settings, and the degree of fine-tuning are not consistent across related work. Which factors contribute to success, and which are accidental? In this work, we address this problem: We systematize audio spoofing detection by re-implementing and uniformly evaluating architectures from related work. We identify overarching features for successful audio deepfake detection, such as using cqtspec or logspec features instead of melspec features, which improves performance by 37% EER on average, all other factors constant. Additionally, we evaluate generalization capabilities: We collect and publish a new dataset consisting of 37.9 hours of found audio recordings of celebrities and politicians, of which 17.2 hours are deepfakes. We find that related work performs poorly on such real-world data (performance degradation of up to one thousand percent). This may suggest that the community has tailored its solutions too closely to the prevailing ASVSpoof benchmark and that deepfakes are much harder to detect outside the lab than previously thought.

comment: Interspeech 2022

♻ ☆ Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs

Sara Papi, Javier Garcia Gilabert, Zachary Hopton, Vilém Zouhar, Carlos Escolano, Gerard I. Gállego, Jorge Iranzo-Sánchez, Ahrii Kim, Dominik Macháček, Patricia Schmidtova, Maike Züfle

As Large Language Models (LLMs) expand beyond text, integrating speech as a native modality has given rise to SpeechLLMs, which directly process spoken language and enable speech-to-text translation (ST) and other downstream tasks, bypassing traditional transcription-based pipelines. Whether this integration improves ST quality over established cascaded architectures, however, remains an open question. We present Hearing to Translate, the first comprehensive test suite rigorously benchmarking 6 state-of-the-art SpeechLLMs against 16 strong direct and cascade systems that couple leading speech foundation models (SFM), with multilingual LLMs. Our analysis spans 16 benchmarks, 13 language pairs, and 9 challenging conditions, including disfluent, noisy, and long-form speech. Across this extensive evaluation, we find that cascaded systems remain the most reliable solution overall, but most recent SpeechLLMs can match or even outperform cascades in various settings while SFMs lag behind both, highlighting that integrating an LLM, either within the model or in a pipeline, is essential for high-quality speech translation.

comment: Project available at https://github.com/sarapapi/hearing2translate

♻ ☆ Hear What Matters! Text-conditioned Selective Video-to-Audio Generation CVPR 2026

Junwon Lee, Juhan Nam, Jiyoung Lee

This work introduces a new task, text-conditioned selective video-to-audio (V2A) generation, which produces only the user-intended sound from a multi-object video. This capability is especially crucial in multimedia production, where audio tracks are handled individually for each sound source for precise editing, mixing, and creative control. We propose SELVA, a novel text-conditioned V2A model that treats the text prompt as an explicit selector to distinctly extract prompt-relevant sound-source visual features from the video encoder. To suppress text-irrelevant activations with efficient video encoder finetuning, the proposed supplementary tokens promote cross-attention to yield robust semantic and temporal grounding. SELVA further employs an autonomous video-mixing scheme in a self-supervised manner to overcome the lack of mono audio track supervision. We evaluate SELVA on VGG-MONOAUDIO, a curated benchmark of clean single-source videos for such a task. Extensive experiments and ablations consistently verify its effectiveness across audio quality, semantic alignment, and temporal synchronization.

comment: accepted to CVPR 2026

♻ ☆ TW-Sound580K: A Regional Audio-Text Dataset with Verification-Guided Curation for Localized Audio-Language Modeling

Hao-Hui Xie, Ho-Lam Chung, Yi-Cheng Lin, Ke-Han Lu, Wenze Ren, Xie Chen, Hung-yi Lee

Large Audio-Language Models (LALMs) typically struggle with localized dialectal prosody due to the scarcity of specialized corpora. We present TW-Sound580K, a Taiwanese audio-text instruction dataset developed through a Verify-Generate-Critique (VGC) protocol. This pipeline leverages Dual-ASR validation to filter 522K raw clips, subsequently expanding them into 580,000 high-fidelity instruction pairs using a teacher model. The dataset's utility is demonstrated through Tai-LALM, which fine-tunes a DeSTA 2.5-Audio-initialized backbone and incorporates a dynamic Dual-ASR Arbitration strategy to optimize transcription selection during inference. On the TAU Benchmark, Tai-LALM reaches 49.1% accuracy, marking a 6.5% absolute improvement over the zero-shot baseline (42.6% with ASR text conditioning). This confirms that integrating regional corpora with rigorous curation and dynamic arbitration significantly enhances LALM performance on localized speech.

comment: The authors have decided to withdraw this submission as the work is no longer intended for public dissemination at this time

♻ ☆ Gelina: Unified Speech and Gesture Synthesis via Interleaved Token Prediction ICASSP 2026

Téo Guichoux, Théodor Lemerle, Shivam Mehta, Jonas Beskow, Gustav Eje Henter, Laure Soulier, Catherine Pelachaud, Nicolas Obin

Human communication is multimodal, with speech and gestures tightly coupled, yet most computational methods for generating speech and gestures synthesize them sequentially, weakening synchrony and prosody alignment. We introduce Gelina, a unified framework that jointly synthesizes speech and co-speech gestures from text using interleaved token sequences in a discrete autoregressive backbone, with modality-specific decoders. Gelina supports multi-speaker and multi-style cloning and enables gesture-only synthesis from speech inputs. Subjective and objective evaluations demonstrate competitive speech quality and improved gesture generation over unimodal baselines.

comment: Paper accepted at ICASSP 2026, 5 pages

♻ ☆ Joint Learning Global-Local Speaker Classification to Enhance End-to-End Speaker Diarization and Recognition

Yuhang Dai, Haopeng Lin, Jiale Qian, Ruiqi Yan, Hao Meng, Hanke Xie, Hanlin Wen, Shunshun Yin, Ming Tao, Xie Chen, Lei Xie, Xinsheng Wang

Large Audio-Language Models (LALMs) have demonstrated remarkable performance in end-to-end speaker diarization and recognition. However, their speaker discriminability remains limited due to the scarcity of large-scale conversational data and the absence of explicit speaker representation optimization. To address this, we propose GLSC-SDR, a paradigm that jointly trains speaker classification with diarization and recognition. We further introduce a Global-Local Speaker Classification strategy, which uses clustered speakers as global labels and re-encoded intra-cluster speakers as local labels. This hierarchical design enhances fine-grained speaker discrimination while preserving semantic transcription accuracy. Experiments on AliMeeting, AISHELL-4, and AMI-SDM demonstrate that GLSC-SDR achieves competitive or superior performance compared to simulation-based and multi-encoder approaches, without relying on large-scale real conversational data.

comment: 5 pages, 2 figures, 2 tables

♻ ☆ DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization CVPR 2026

Ngoc-Son Nguyen, Thanh V. T. Tran, Jeongsoo Choi, Hieu-Nghia Huynh-Nguyen, Truong-Son Hy, Van Nguyen

Video dubbing has broad applications in filmmaking, multimedia creation, and assistive speech technology. Existing approaches either train directly on limited dubbing datasets or adopt a two-stage pipeline that adapts pre-trained text-to-speech (TTS) models, which often struggle to produce expressive prosody, rich acoustic characteristics, and precise synchronization. To address these issues, we propose DiFlowDubber with a novel two-stage training framework that effectively transfers knowledge from a pre-trained TTS model to video-driven dubbing, with a discrete flow matching generative backbone. Specifically, we design a FaPro module that captures global prosody and stylistic cues from facial expressions and leverages this information to guide the modeling of subsequent speech attributes. To ensure precise speech-lip synchronization, we introduce a Synchronizer module that bridges the modality gap among text, video, and speech, thereby improving cross-modal alignment and generating speech that is temporally synchronized with lip movements. Experiments on two primary benchmark datasets demonstrate that DiFlowDubber outperforms previous methods across multiple metrics.

comment: Accepted at CVPR 2026 Findings

♻ ☆ Acoustic Imaging for UAV Detection: Dense Beamformed Energy Maps and U-Net SELD

Belman Jahir Rodriguez, Sergio F. Chevtchenko, Marcelo Herrera Martinez, Yeshwanth Bethi, Saeed Afshar

We introduce a U-net model for 360° acoustic source localization formulated as a spherical semantic segmentation task. Rather than regressing discrete direction-of-arrival (DoA) angles, our model segments beamformed audio maps (azimuth & elevation) into regions of active sound presence. Using delay-and-sum (DAS) beamforming on a custom 24-microphone array, we generate signals aligned with drone GPS telemetry to create binary supervision masks. A modified U-Net, trained on frequency-domain representations of these maps, learns to identify spatially distributed source regions while addressing class imbalance via the Tversky loss. Because the network operates on beamformed energy maps, the approach is inherently array-independent and can adapt to different microphone configurations and can be transferred to different microphone configurations with minimal adaptation. The segmentation outputs are post-processed by computing centroids over activated regions, enabling robust DoA estimates. Our dataset includes real-world open-field recordings of a DJI Air 3 drone, synchronized with 360° video and flight logs across multiple dates and locations. Experimental results show that U-net generalizes across environments, providing improved angular precision, offering a new paradigm for dense spatial audio understanding beyond traditional Sound Source Localization (SSL). We additionally validate the same beamforming-plus-segmentation formulation on the DCASE 2019 TAU Spatial Sound Events benchmark, showing that the approach generalizes beyond drone acoustics to multiclass Sound Event Localization and Detection (SELD) scenarios.

Audio and Speech Processing 13

☆ PHONOS: PHOnetic Neutralization for Online Streaming Applications

Waris Quamer, Mu-Ruei Tseng, Ghady Nasrallah, Ricardo Gutierrez-Osuna

Speaker anonymization (SA) systems modify timbre while leaving regional or non-native accents intact, which is problematic because accents can narrow the anonymity set. To address this issue, we present PHONOS, a streaming module for real-time SA that neutralizes non-native accent to sound native-like. Our approach pre-generates golden speaker utterances that preserve source timbre and rhythm but replace foreign segmentals with native ones using silence-aware DTW alignment and zero-shot voice conversion. These utterances supervise a causal accent translator that maps non-native content tokens to native equivalents with at most 40ms look-ahead, trained using joint cross-entropy and CTC losses. Our evaluations show an 81% reduction in non-native accent confidence, with listening-test ratings consistent with this shift, and reduced speaker linkability as accent-neutralized utterances move away from the original speaker in embedding space while having latency under 241 ms on single GPU.

comment: The paper is submitted to Interspeech 2026 and currently under review

☆ Rhythmic segment analysis: Conceptualizing, visualizing, and measuring rhythmic data

Bas Cornelissen

comment: 15 pages, 7 figures

☆ Multilingual Stutter Event Detection for English, German, and Mandarin Speech

Felix Haas, Sebastian P. Bayerl

☆ AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection

Hai-Son Nguyen-Le, Hung-Cuong Nguyen-Thanh, Nhien-An Le-Khac, Dinh-Thuc Nguyen, Hong-Hanh Nguyen-Le

comment: Accepted at International Joint Conference on Neural Networks 2026

☆ A Power-Weighted Noncentral Complex Gaussian Distribution

Toru Nakashika

☆ Distilling Conversations: Abstract Compression of Conversational Audio Context for LLM-based ASR

Shashi Kumar, Esaú Villatoro-Tello, Sergio Burdisso, Kadri Hacioglu, Thibault Bañeras-Roux, Hasindri Watawana, Dairazalia Sanchez-Cortes, Srikanth Madikeri, Petr Motlicek, Andreas Stolcke

Standard LLM-based speech recognition systems typically process utterances in isolation, limiting their ability to leverage conversational context. In this work, we study whether multimodal context from prior turns improves LLM-based ASR and how to represent that context efficiently. We find that, after supervised multi-turn training, conversational context mainly helps with the recognition of contextual entities. However, conditioning on raw context is expensive because the prior-turn audio token sequence grows rapidly with conversation length. To address this, we propose Abstract Compression, which replaces the audio portion of prior turns with a fixed number of learned latent tokens while retaining corresponding transcripts explicitly. On both in-domain and out-of-domain test sets, the compressed model recovers part of the gains of raw-context conditioning with a smaller prior-turn audio footprint. We also provide targeted analyses of the compression setup and its trade-offs.

comment: 11 pages

☆ Dual-branch Graph Domain Adaptation for Cross-scenario Multi-modal Emotion Recognition

Yuntao Shou, Jun Zhou, Tao Meng, Wei Ai, Keqin Li

Multimodal Emotion Recognition in Conversations (MERC) aims to predict speakers' emotional states in multi-turn dialogues through text, audio, and visual cues. In real-world settings, conversation scenarios differ significantly in speakers, topics, styles, and noise levels. Existing MERC methods generally neglect these cross-scenario variations, limiting their ability to transfer models trained on a source domain to unseen target domains. To address this issue, we propose a Dual-branch Graph Domain Adaptation framework (DGDA) for multimodal emotion recognition under cross-scenario conditions. We first construct an emotion interaction graph to characterize complex emotional dependencies among utterances. A dual-branch encoder, consisting of a hypergraph neural network (HGNN) and a path neural network (PathNN), is then designed to explicitly model multivariate relationships and implicitly capture global dependencies. To enable out-of-domain generalization, a domain adversarial discriminator is introduced to learn invariant representations across domains. Furthermore, a regularization loss is incorporated to suppress the negative influence of noisy labels. To the best of our knowledge, DGDA is the first MERC framework that jointly addresses domain shift and label noise. Theoretical analysis provides tighter generalization bounds, and extensive experiments on IEMOCAP and MELD demonstrate that DGDA consistently outperforms strong baselines and better adapts to cross-scenario conversations. Our code is available at https://github.com/Xudmm1239439/DGDA-Net.

comment: 29 pages

☆ Cinematic Audio Source Separation Using Visual Cues CVPR 2026

Kang Zhang, Suyeon Lee, Arda Senocak, Joon Son Chung

comment: CVPR 2026. Project page: https://cass-flowmatching.github.io

♻ ☆ DiffAU: Diffusion-Based Ambisonics Upscaling

Amit Milstein, Nir Shlezinger, Boaz Rafaely

♻ ☆ Does Audio Deepfake Detection Generalize?

Nicolas M. Müller, Pavel Czempin, Franziska Dieckmann, Adam Froghyar, Konstantin Böttinger

comment: Interspeech 2022

♻ ☆ Hear What Matters! Text-conditioned Selective Video-to-Audio Generation CVPR 2026

Junwon Lee, Juhan Nam, Jiyoung Lee

comment: accepted to CVPR 2026

♻ ☆ Gelina: Unified Speech and Gesture Synthesis via Interleaved Token Prediction ICASSP 2026

Téo Guichoux, Théodor Lemerle, Shivam Mehta, Jonas Beskow, Gustav Eje Henter, Laure Soulier, Catherine Pelachaud, Nicolas Obin

comment: Paper accepted at ICASSP 2026, 5 pages

♻ ☆ Acoustic Imaging for UAV Detection: Dense Beamformed Energy Maps and U-Net SELD

Belman Jahir Rodriguez, Sergio F. Chevtchenko, Marcelo Herrera Martinez, Yeshwanth Bethi, Saeed Afshar

2026-03-26

Sound 13

☆ CLAR: CIF-Localized Alignment for Retrieval-Augmented Speech LLM-Based Contextual ASR

Shangkun Huang, Huan Shen, Wei Zou, Yunzhang Chen

Speech LLM-based ASR often struggles with named entities and long-tail words due to strong internal language-model priors. Retrieval-augmented biasing can help, but its effectiveness depends on accurate hotword localization in full-utterance speech under weak supervision. We propose CLAR, a dual-encoder speech-text retriever that uses Continuous Integrate-and-Fire (CIF) to learn monotonic token-level alignments without timestamps. With length-aware localized matching, CLAR anchors short-entity acoustic cues and reduces representation dilution and attention drift. The retriever is trained with a multi-granularity objective combining global and local segment-level contrastive losses and a CIF quantity constraint. At inference, top-ranked hotwords are injected as contextual prompts for the Speech LLM, improving recognition without shallow fusion. Experiments show that CLAR significantly improves hotword retrieval and reduces both CER and B-WER against strong contextual ASR baselines.

comment: Submitted to Interspeech 2026

☆ CoDeTT: A Context-Aware Decision Benchmark for Turn-Taking Evaluation

Huan Shen, Yingao Wang, Shangkun Huang, Wei Zou, Yunzhang Chen

comment: Submitted to Interspeech 2026

☆ Joint Learning Global-Local Speaker Classification to Enhance End-to-End Speaker Diarization and Recognition

Yuhang Dai, Haopeng Lin, Jiale Qian, Ruiqi Yan, Hao Meng, Hanke Xie, Hanlin Wen, Shunshun Yin, Ming Tao, Xie Chen, Lei Xie, Xinsheng Wang

comment: 5 pages, 2 figures, 2 tables

☆ SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment

Sahibzada Adil Shahzad, Ammarah Hashmi, Junichi Yamagishi, Yusuke Yasuda, Yu Tsao, Chia-Wen Lin, Yan-Tsung Peng, Hsin-Min Wang

Multimodal deepfakes can exhibit subtle visual artifacts and cross-modal inconsistencies, which remain challenging to detect, especially when detectors are trained primarily on curated synthetic forgeries. Such synthetic dependence can introduce dataset and generator bias, limiting scalability and robustness to unseen manipulations. We propose SAVe, a self-supervised audio-visual deepfake detection framework that learns entirely on authentic videos. SAVe generates on-the-fly, identity-preserving, region-aware self-blended pseudo-manipulations to emulate tampering artifacts, enabling the model to learn complementary visual cues across multiple facial granularities. To capture cross-modal evidence, SAVe also models lip-speech synchronization via an audio-visual alignment component that detects temporal misalignment patterns characteristic of audio-visual forgeries. Experiments on FakeAVCeleb and AV-LipSync-TIMIT demonstrate competitive in-domain performance and strong cross-dataset generalization, highlighting self-supervised learning as a scalable paradigm for multimodal deepfake detection.

☆ Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods CVPR 2026

Xuanru Zhou, Yiwen Shao, Wei-Cheng Tseng, Dong Yu

Current audio pre-training seeks to learn unified representations for broad audio understanding tasks, but it remains fragmented and is fundamentally bottlenecked by its reliance on weak, noisy, and scale-limited labels. Drawing lessons from vision's foundational pre-training blueprint, we argue that the audio field must first establish its own large-scale, strong supervision framework. We introduce a new data-centric pipeline that leverages a high-fidelity captioner to create SOTA-quality captions and the first Unified Tag System (UTS) that bridges speech, music, and environmental sounds. We then conduct a systematic comparative study of different pre-training objectives on these strong source data. Our experiments suggest that data quality and coverage are the primary drivers of performance, while the choice of objective dictates downstream task specialization.

comment: Accepted to CVPR 2026

♻ ☆ Enhancing Automatic Chord Recognition via Pseudo-Labeling and Knowledge Distillation

Nghia Phan, Rong Jin, Gang Liu, Xiao Dong

Automatic Chord Recognition (ACR) is constrained by the scarcity of aligned chord labels, as well-aligned annotations are costly to acquire. At the same time, open-weight pre-trained models are currently more accessible than their proprietary training data. In this work, we present a two-stage training pipeline that leverages pre-trained models together with unlabeled audio. The proposed method decouples training into two stages. In the first stage, we use a pre-trained BTC model as a teacher to generate pseudo-labels for over 1,000 hours of diverse unlabeled audio and train a student model solely on these pseudo-labels. In the second stage, the student is continually trained on ground-truth labels as they become available. To prevent catastrophic forgetting of the representations learned in the first stage, we apply selective knowledge distillation (KD) from the teacher as a regularizer. In our experiments, two models (BTC, 2E1D) were used as students. In stage 1, using only pseudo-labels, the BTC student achieves over 98% of the teacher's performance, while the 2E1D model achieves about 96% across seven standard mir_eval metrics. After a single training run for both students in stage 2, the resulting BTC student model surpasses the traditional supervised learning baseline by 2.5% and the original pre-trained teacher model by 1.55% on average across all metrics. The resulting 2E1D student model improves over the traditional supervised learning baseline by 2.67% on average and achieves almost the same performance as the teacher. Both cases show large gains on rare chord qualities.

comment: 9 pages, 6 figures, 3 tables

♻ ☆ ASVspoof 5: Evaluation of Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech

Xin Wang, Héctor Delgado, Nicholas Evans, Xuechen Liu, Tomi Kinnunen, Hemlata Tak, Kong Aik Lee, Ivan Kukanov, Md Sahidullah, Massimiliano Todisco, Junichi Yamagishi

ASVspoof 5 is the fifth edition in a series of challenges which promote the study of speech spoofing and deepfake detection solutions. A significant change from previous challenge editions is a new crowdsourced database collected from a substantially greater number of speakers under diverse recording conditions, and a mix of cutting-edge and legacy generative speech technology. With the new database described elsewhere, we provide in this paper an overview of the ASVspoof 5 challenge results for the submissions of 53 participating teams. While many solutions perform well, performance degrades under adversarial attacks and the application of neural encoding/compression schemes. Together with a review of post-challenge results, we also report a study of calibration in addition to other principal challenges and outline a road-map for the future of ASVspoof.

comment: This work has been submitted to the IEEE TASLP for possible publication

♻ ☆ U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model

Louis Bahrman, Marius Rodrigues, Mathieu Fontaine, Gaël Richard

This paper explores the outcome of training state-of-the-art dereverberation models with supervision settings ranging from weakly-supervised to virtually unsupervised, relying solely on reverberant signals and an acoustic model for training. Most of the existing deep learning approaches typically require paired dry and reverberant data, which are difficult to obtain in practice. We develop instead a sequential learning strategy motivated by a maximum-likelihood formulation of the dereverberation problem, wherein acoustic parameters and dry signals are estimated from reverberant inputs using deep neural networks, guided by a reverberation matching loss. Our most data-efficient variant requires only 100 reverberation-parameter-labeled samples to outperform an unsupervised baseline, demonstrating the effectiveness and practicality of the proposed method in low-resource scenarios.

♻ ☆ Enhancing Efficiency and Performance in Deepfake Audio Detection through Neuron-level Dropin & Neuroplasticity Mechanisms IJCNN 2026

Yupei Li, Shuaijie Shao, Manuel Milling, Björn Schuller

Current audio deepfake detection has achieved remarkable performance using diverse deep learning architectures such as ResNet, and has seen further improvements with the introduction of large models (LMs) like Wav2Vec. The success of large language models (LLMs) further demonstrates the benefits of scaling model parameters, but also highlights one bottleneck where performance gains are constrained by parameter counts. Simply stacking additional layers, as done in current LLMs, is computationally expensive and requires full retraining. Furthermore, existing low-rank adaptation methods are primarily applied to attention-based architectures, which limits their scope. Inspired by the neuronal plasticity observed in mammalian brains, we propose novel algorithms, dropin and further plasticity, that dynamically adjust the number of neurons in certain layers to flexibly modulate model parameters. We evaluate these algorithms on multiple architectures, including ResNet, Gated Recurrent Neural Networks, and Wav2Vec. Experimental results using the widely recognised ASVSpoof2019 LA, PA, and FakeorReal dataset demonstrate consistent improvements in computational efficiency with the dropin approach and a maximum of around 39% and 66% relative reduction in Equal Error Rate with the dropin and plasticity approach among these dataset, respectively. The code and supplementary material are available at Github link.

comment: Accepted at IJCNN 2026

♻ ☆ DashengTokenizer: One layer is enough for unified audio understanding and generation

Heinrich Dinkel, Xingwei Sun, Gang Li, Jiahao Mei, Yadong Niu, Jizhong Liu, Xiyang Li, Yifan Liao, Jiahao Zhou, Junbo Zhang, Jian Luan

This paper introduces DashengTokenizer, a continuous audio tokenizer engineered for joint use in both understanding and generation tasks. Unlike conventional approaches, which train acoustic tokenizers and subsequently integrate frozen semantic knowledge, our method inverts this paradigm: we leverage frozen semantic features and inject acoustic information. In linear evaluation across 22 diverse tasks, our method outperforms previous audio codec and audio encoder baselines by a significant margin while maintaining competitive audio reconstruction quality. Notably, we demonstrate that this acoustic injection improves performance for tasks such as speech emotion recognition, music understanding, and acoustic scene classification. We further evaluate the tokenizer's generative performance on text-to-audio (TTA), text-to-music (TTM), and speech enhancement (SE). Our approach surpasses standard variational autoencoder (VAE)-based methods on TTA and TTM tasks, while its effectiveness on SE underscores its capabilities as a general-purpose audio encoder. Finally, our results challenge the prevailing assumption that VAE-based architectures are a prerequisite for audio synthesis. Checkpoints are available at https://huggingface.co/mispeech/dashengtokenizer.

comment: Added ACAVCaps reference

♻ ☆ MiDashengLM: Efficient Audio Understanding with General Audio Captions ICASSP 2026

Heinrich Dinkel, Gang Li, Jizhong Liu, Jian Luan, Yadong Niu, Xingwei Sun, Tianzi Wang, Qiyang Xiao, Junbo Zhang, Jiahao Zhou

Current approaches for large audio language models (LALMs) often rely on closed data sources or proprietary models, limiting their generalization and accessibility. This paper introduces MiDashengLM, a novel open audio-language model designed for efficient and comprehensive audio understanding through the use of general audio captions using our novel ACAVCaps training dataset. MiDashengLM exclusively relies on publicly available pretraining and supervised fine-tuning (SFT) datasets, ensuring full transparency and reproducibility. At its core, MiDashengLM integrates Dasheng, an open-source audio encoder, specifically engineered to process diverse auditory information effectively. Unlike previous works primarily focused on Automatic Speech Recognition (ASR) based audio-text alignment, our strategy centers on general audio captions, fusing speech, sound and music information into one textual representation, enabling a holistic textual representation of complex audio scenes. Lastly, MiDashengLM provides an up to 4x speedup in terms of time-to-first-token (TTFT) and up to 20x higher throughput than comparable models. Checkpoints are available online at https://huggingface.co/mispeech/midashenglm-7b and https://github.com/xiaomi-research/dasheng-lm.

comment: Added ACAVCaps reference (ICASSP 2026)

♻ ☆ A Lightweight Two-Branch Architecture for Multi-instrument Transcription via Note-Level Contrastive Clustering

Ruigang Li, Yongxu Zhu

Existing multi-timbre transcription models struggle with generalization beyond pre-trained instruments, rigid source-count constraints, and high computational demands that hinder deployment on low-resource devices. We address these limitations with a lightweight model that extends a timbre-agnostic transcription backbone with a dedicated timbre encoder and performs deep clustering at the note level, enabling joint transcription and dynamic separation of arbitrary instruments given a specified number of instrument classes. Practical optimizations including spectral normalization, dilated convolutions, and contrastive clustering further improve efficiency and robustness. Despite its small size and fast inference, the model achieves competitive performance with heavier baselines in terms of transcription accuracy and separation quality, and shows promising generalization ability, making it highly suitable for real-world deployment in practical and resource-constrained settings.

♻ ☆ Acoustic Imaging for Low-SNR UAV Detection: Dense Beamformed Energy Maps and U-Net SELD

Belman Jahir Rodriguez, Sergio F. Chevtchenko, Marcelo Herrera Martinez, Yeshwant Bethy, Saeed Afshar

We introduce a U-net model for 360° acoustic source localization formulated as a spherical semantic segmentation task. Rather than regressing discrete direction-of-arrival (DoA) angles, our model segments beamformed audio maps (azimuth and elevation) into regions of active sound presence. Using delay-and-sum (DAS) beamforming on a custom 24-microphone array, we generate signals aligned with drone GPS telemetry to create binary supervision masks. A modified U-Net, trained on frequency-domain representations of these maps, learns to identify spatially distributed source regions while addressing class imbalance via the Tversky loss. Because the network operates on beamformed energy maps, the approach is inherently array-independent and can adapt to different microphone configurations without retraining from scratch. The segmentation outputs are post-processed by computing centroids over activated regions, enabling robust DoA estimates. Our dataset includes real-world open-field recordings of a DJI Air 3 drone, synchronized with 360° video and flight logs across multiple dates and locations. Experimental results show that U-net generalizes across environments, providing improved angular precision, offering a new paradigm for dense spatial audio understanding beyond traditional Sound Source Localization (SSL).

Audio and Speech Processing 7

☆ AdaLTM: Adaptive Layer-wise Task Vector Merging for Categorical Speech Emotion Recognition with ASR Knowledge Integration

Chia-Yu Lee, Huang-Cheng Chou, Tzu-Quan Lin, Yuanchao Li, Ya-Tse Wu, Shrikanth Narayanan, Chi-Chun Lee

Integrating Automatic Speech Recognition (ASR) into Speech Emotion Recognition (SER) enhances modeling by providing linguistic context. However, conventional feature fusion faces performance bottlenecks, and multi-task learning often suffers from optimization conflicts. While task vectors and model merging have addressed such conflicts in NLP and CV, their potential in speech tasks remains largely unexplored. In this work, we propose an Adaptive Layer-wise Task Vector Merging (AdaLTM) framework based on WavLM-Large. Instead of joint optimization, we extract task vectors from in-domain ASR and SER models fine-tuned on emotion datasets. These vectors are integrated into a frozen base model using layer-wise learnable coefficients. This strategy enables depth-aware balancing of linguistic and paralinguistic knowledge across transformer layers without gradient interference. Experiments on the MSP-Podcast demonstrate that the proposed approach effectively mitigates conflicts between ASR and SER.

comment: Submitted to Interspeech 2026

☆ UPV_RIR_DB: A Structured Room Impulse Response Database with Hierarchical Metadata and Acoustic Indicators

Jesús García-Gamborino, Laura Fuster, Daniel de la Prida, Luis A. Azpicueta-Ruiz, Gema Piñero

This paper presents UPV_RIR_DB, a structured database of measured room impulse responses (RIRs) designed to provide acoustic data with explicit spatial metadata and traceable acquisition parameters. The dataset currently contains 166 multichannel RIR files measured in three rooms of the Universitat Politècnica de València (UPV). Each multichannel RIR file contains impulse responses for multiple source-receiver pairs, with each pair covering a 25 cm2 area - the typical size of a personal sound zone. Considering the number of sources and receiver channels associated with each microphone modality, the database contains a total of 18,976 single impulse responses. A hierarchical organization is adopted in which directory structure and metadata jointly describe the measurement context. Each room includes a metadata file containing acquisition parameters, hardware description, spatial coordinates of zones and microphones, and acoustic indicators such as reverberation time. A central index links each RIR file with its experimental context, ensuring traceability and enabling reproducible analysis. The resulting database provides a consistent framework for storing, inspecting, and reusing real RIR measurements while preserving compatibility with both MATLAB- and JSON-based workflows. The UPV_RIR_DB dataset is publicly available through the open repository Zenodo.

comment: RIR Database available at ZENODO

☆ Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods CVPR 2026

Xuanru Zhou, Yiwen Shao, Wei-Cheng Tseng, Dong Yu

comment: Accepted to CVPR 2026

♻ ☆ U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model

Louis Bahrman, Marius Rodrigues, Mathieu Fontaine, Gaël Richard

♻ ☆ DashengTokenizer: One layer is enough for unified audio understanding and generation

Heinrich Dinkel, Xingwei Sun, Gang Li, Jiahao Mei, Yadong Niu, Jizhong Liu, Xiyang Li, Yifan Liao, Jiahao Zhou, Junbo Zhang, Jian Luan

comment: Added ACAVCaps reference

♻ ☆ MiDashengLM: Efficient Audio Understanding with General Audio Captions ICASSP 2026

Heinrich Dinkel, Gang Li, Jizhong Liu, Jian Luan, Yadong Niu, Xingwei Sun, Tianzi Wang, Qiyang Xiao, Junbo Zhang, Jiahao Zhou

comment: Added ACAVCaps reference (ICASSP 2026)

♻ ☆ Acoustic Imaging for Low-SNR UAV Detection: Dense Beamformed Energy Maps and U-Net SELD

Belman Jahir Rodriguez, Sergio F. Chevtchenko, Marcelo Herrera Martinez, Yeshwant Bethy, Saeed Afshar

We introduce a U-net model for 360° acoustic source localization formulated as a spherical semantic segmentation task. Rather than regressing discrete direction-of-arrival (DoA) angles, our model segments beamformed audio maps (azimuth and elevation) into regions of active sound presence. Using delay-and-sum (DAS) beamforming on a custom 24-microphone array, we generate signals aligned with drone GPS telemetry to create binary supervision masks. A modified U-Net, trained on frequency-domain representations of these maps, learns to identify spatially distributed source regions while addressing class imbalance via the Tversky loss. Because the network operates on beamformed energy maps, the approach is inherently array-independent and can adapt to different microphone configurations without retraining from scratch. The segmentation outputs are post-processed by computing centroids over activated regions, enabling robust DoA estimates. Our dataset includes real-world open-field recordings of a DJI Air 3 drone, synchronized with 360° video and flight logs across multiple dates and locations. Experimental results show that U-net generalizes across environments, providing improved angular precision, offering a new paradigm for dense spatial audio understanding beyond traditional Sound Source Localization (SSL).

2026-03-25

Sound 16

☆ YingMusic-Singer: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance

Chunbo Hao, Junjie Zheng, Guobin Ma, Yuepeng Jiang, Huakang Chen, Wenjie Tian, Gongyu Chen, Zihao Chen, Lei Xie

Regenerating singing voices with altered lyrics while preserving melody consistency remains challenging, as existing methods either offer limited controllability or require laborious manual alignment. We propose YingMusic-Singer, a fully diffusion-based model enabling melody-controllable singing voice synthesis with flexible lyric manipulation. The model takes three inputs: an optional timbre reference, a melody-providing singing clip, and modified lyrics, without manual alignment. Trained with curriculum learning and Group Relative Policy Optimization, YingMusic-Singer achieves stronger melody preservation and lyric adherence than Vevo2, the most comparable baseline supporting melody control without manual alignment. We also introduce LyricEditBench, the first benchmark for melody-preserving lyric modification evaluation. The code, weights, benchmark, and demos are publicly available at https://github.com/ASLP-lab/YingMusic-Singer.

☆ A Sociolinguistic Analysis of Automatic Speech Recognition Bias in Newcastle English

Dana Serditova, Kevin Tang

Automatic Speech Recognition (ASR) systems are widely used in everyday communication, education, healthcare, and industry, yet their performance remains uneven across speakers, particularly when dialectal variation diverges from the mainstream accents represented in training data. This study investigates ASR bias through a sociolinguistic analysis of Newcastle English, a regional variety of North-East England that has been shown to challenge current speech recognition technologies. Using spontaneous speech from the Diachronic Electronic Corpus of Tyneside English (DECTE), we evaluate the output of a state-of-the-art commercial ASR system and conduct a fine-grained analysis of more than 3,000 transcription errors. Errors are classified by linguistic domain and examined in relation to social variables including gender, age, and socioeconomic status. In addition, an acoustic case study of selected vowel features demonstrates how gradient phonetic variation contributes directly to misrecognition. The results show that phonological variation accounts for the majority of errors, with recurrent failures linked to dialect-specific features like vowel quality and glottalisation, as well as local vocabulary and non-standard grammatical forms. Error rates also vary across social groups, with higher error frequencies observed for men and for speakers at the extremes of the age spectrum. These findings indicate that ASR errors are not random but socially patterned and can be explained from a sociolinguistic perspective. Thus, the study demonstrates the importance of incorporating sociolinguistic expertise into the evaluation and development of speech technologies and argues that more equitable ASR systems require explicit attention to dialectal variation and community-based speech data.

comment: 54 pages, 11 figures

☆ What and When to Learn: CURriculum Ranking Loss for Large-Scale Speaker Verification

Massa Baali, Sarthak Bisht, Rita Singh, Bhiksha Raj

Speaker verification at large scale remains an open challenge as fixed-margin losses treat all samples equally regardless of quality. We hypothesize that mislabeled or degraded samples introduce noisy gradients that disrupt compact speaker manifolds. We propose Curry (CURriculum Ranking), an adaptive loss that estimates sample difficulty online via Sub-center ArcFace: confidence scores from dominant sub-center cosine similarity rank samples into easy, medium, and hard tiers using running batch statistics, without auxiliary annotations. Learnable weights guide the model from stable identity foundations through manifold refinement to boundary sharpening. To our knowledge, this is the largest-scale speaker verification system trained to date. Evaluated on VoxCeleb1-O, and SITW, Curry reduces EER by 86.8\% and 60.0\% over the Sub-center ArcFace baseline, establishing a new paradigm for robust speaker verification on imperfect large-scale data.

☆ Iterate to Differentiate: Enhancing Discriminability and Reliability in Zero-Shot TTS Evaluation

Shengfan Shen, Di Wu, Xingchen Song, Dinghao Zhou, Liumeng Xue, Meng Meng, Jian Luan, Shuai Wang

Reliable evaluation of modern zero-shot text-to-speech (TTS) models remains challenging. Subjective tests are costly and hard to reproduce, while objective metrics often saturate, failing to distinguish SOTA systems. To address this, we propose Iterate to Differentiate (I2D), an evaluation framework that recursively synthesizes speech using the model's own outputs as references. Higher-quality models exhibit greater resilience to the distributional shift induced by iterative synthesis, resulting in slower performance degradation. I2D exploits this differential degradation to amplify performance gaps and reveal robustness. By aggregating objective metrics across iterations, I2D improves discriminability and alignment with human judgments, increasing system-level SRCC from 0.118 to 0.464 for UTMOSv2. Experiments on 11 models across Chinese, English, and emotion datasets demonstrate that I2D enables more reliable automated evaluation for zero-shot TTS.

comment: submitted to Interspeech 2026, under review

☆ Enhancing Efficiency and Performance in Deepfake Audio Detection through Neuron-level dropin & Neuroplasticity Mechanisms IJCNN 2026

Yupei Li, Shuaijie Shao, Manuel Milling, Björn Schuller

comment: Accepted at IJCNN 2026

☆ Bridging Biological Hearing and Neuromorphic Computing: End-to-End Time-Domain Audio Signal Processing with Reservoir Computing

Rinku Sebastian, Simon O'Keefe, Martin Trefzer

Despite the advancements in cutting-edge technologies, audio signal processing continues to pose challenges and lacks the precision of a human speech processing system. To address these challenges, we propose a novel approach to simplify audio signal processing by leveraging time-domain techniques and reservoir computing. Through our research, we have developed a real-time audio signal processing system by simplifying audio signal processing through the utilization of reservoir computers, which are significantly easier to train. Feature extraction is a fundamental step in speech signal processing, with Mel Frequency Cepstral Coefficients (MFCCs) being a dominant choice due to their perceptual relevance to human hearing. However, conventional MFCC extraction relies on computationally intensive time-frequency transformations, limiting efficiency in real-time applications. To address this, we propose a novel approach that leverages reservoir computing to streamline MFCC extraction. By replacing traditional frequency-domain conversions with convolution operations, we eliminate the need for complex transformations while maintaining feature discriminability. We present an end-to-end audio processing framework that integrates this method, demonstrating its potential for efficient and real-time speech analysis. Our results contribute to the advancement of energy-efficient audio processing technologies, enabling seamless deployment in embedded systems and voice-driven applications. This work bridges the gap between biologically inspired feature extraction and modern neuromorphic computing, offering a scalable solution for next-generation speech recognition systems.

☆ Semantic-Aware Interruption Detection in Spoken Dialogue Systems: Benchmark, Metric, and Model ICME 2026

Kangxiang Xia, Bingshen Mu, Xian Shi, Jin Xu, Lei Xie

Achieving natural full-duplex interaction in spoken dialogue systems (SDS) remains a challenge due to the difficulty of accurately detecting user interruptions. Current solutions are polarized between "trigger-happy" VAD-based methods that misinterpret backchannels and robust end-to-end models that exhibit unacceptable response delays. Moreover, the absence of real-world benchmarks and holistic metrics hinders progress in the field. This paper presents a comprehensive frame-work to overcome these limitations. We first introduce SID-Bench, the first benchmark for semantic-aware interruption detection built entirely from real-world human dialogues. To provide a rigorous assessment of the responsiveness-robustness trade-off, we propose the Average Penalty Time (APT) metric, which assigns a temporal cost to both false alarms and late responses. Building on this framework, we design an LLM-based detection model optimized through a novel training paradigm to capture subtle semantic cues of intent. Experimental results show that our model significantly outperforms mainstream baselines, achieving a nearly threefold reduction in APT. By successfully resolving the long-standing tension between speed and stability, our work establishes a new state-of-the-art for intelligent interruption handling in SDS. To facilitate future research, SID-Bench and the associated code are available at: https://github.com/xkx-hub/SID-bench.

comment: Accepted by ICME 2026

☆ ACAVCaps: Enabling large-scale training for fine-grained and diverse audio understanding ICASSP 2026

Yadong Niu, Tianzi Wang, Heinrich Dinkel, Xingwei Sun, Jiahao Zhou, Gang Li, Jizhong Liu, Junbo Zhang, Jian Luan

General audio understanding is a fundamental goal for large audio-language models, with audio captioning serving as a cornerstone task for their development. However, progress in this domain is hindered by existing datasets, which lack the scale and descriptive granularity required to train truly versatile models. To address this gap, we introduce ACAVCaps, a new large-scale, fine-grained, and multi-faceted audio captioning dataset. Derived from the ACAV100M collection, ACAVCaps is constructed using a multi-expert pipeline that analyzes audio from diverse perspectives-including speech, music, and acoustic properties-which are then synthesized into rich, detailed descriptions by a large language model. Experimental results demonstrate that models pre-trained on ACAVCaps exhibit substantially stronger generalization capabilities on various downstream tasks compared to those trained on other leading captioning datasets. The dataset is available at https://github.com/xiaomi-research/acavcaps.

comment: accepted by ICASSP 2026

☆ Variable-Length Audio Fingerprinting

Hongjie Chen, Hanyu Meng, Huimin Zeng, Ryan A. Rossi, Lie Lu, Josh Kimball

Audio fingerprinting converts audio to much lower-dimensional representations, allowing distorted recordings to still be recognized as their originals through similar fingerprints. Existing deep learning approaches rigidly fingerprint fixed-length audio segments, thereby neglecting temporal dynamics during segmentation. To address limitations due to this rigidity, we propose Variable-Length Audio FingerPrinting (VLAFP), a novel method that supports variable-length fingerprinting. To the best of our knowledge, VLAFP is the first deep audio fingerprinting model capable of processing audio of variable length, for both training and testing. Our experiments show that VLAFP outperforms existing state-of-the-arts in live audio identification and audio retrieval across three real-world datasets.

☆ Rethinking Masking Strategies for Masked Prediction-based Audio Self-supervised Learning IJCNN 2026

Daisuke Niizumi, Daiki Takeuchi, Masahiro Yasuda, Binh Thien Nguyen, Noboru Harada, Nobutaka Ono

Since the introduction of Masked Autoencoders, various improvements to masking techniques have been explored. In this paper, we rethink masking strategies for audio representation learning using masked prediction-based self-supervised learning (SSL) on general audio spectrograms. While recent informed masking techniques have attracted attention, we observe that they incur substantial computational overhead. Motivated by this observation, we propose dispersion-weighted masking (DWM), a lightweight masking strategy that leverages the spectral sparsity inherent in the frequency structure of audio content. Our experiments show that inverse block masking, commonly used in recent SSL frameworks, improves audio event understanding performance while introducing a trade-off in generalization. The proposed DWM alleviates these limitations and computational complexity, leading to consistent performance improvements. This work provides practical guidance on masking strategy design for masked prediction-based audio representation learning.

comment: 6+1 pages, 2 figures, 3 tables, accepted at IJCNN 2026

☆ AVControl: Efficient Framework for Training Audio-Visual Controls

Matan Ben-Yosef, Tavi Halperin, Naomi Ken Korem, Mohammad Salama, Harel Cain, Asaf Joseph, Anthony Chen, Urska Jelercic, Ofir Bibi

Controlling video and audio generation requires diverse modalities, from depth and pose to camera trajectories and audio transformations, yet existing approaches either train a single monolithic model for a fixed set of controls or introduce costly architectural changes for each new modality. We introduce AVControl, a lightweight, extendable framework built on LTX-2, a joint audio-visual foundation model, where each control modality is trained as a separate LoRA on a parallel canvas that provides the reference signal as additional tokens in the attention layers, requiring no architectural changes beyond the LoRA adapters themselves. We show that simply extending image-based in-context methods to video fails for structural control, and that our parallel canvas approach resolves this. On the VACE Benchmark, we outperform all evaluated baselines on depth- and pose-guided generation, inpainting, and outpainting, and show competitive results on camera control and audio-visual benchmarks. Our framework supports a diverse set of independently trained modalities: spatially-aligned controls such as depth, pose, and edges, camera trajectory with intrinsics, sparse motion control, video editing, and, to our knowledge, the first modular audio-visual controls for a joint generation model. Our method is both compute- and data-efficient: each modality requires only a small dataset and converges within a few hundred to a few thousand training steps, a fraction of the budget of monolithic alternatives. We publicly release our code and trained LoRA checkpoints.

comment: Project page: https://matanby.github.io/AVControl/

☆ When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews LREC 2026

Hasindri Watawana, Sergio Burdisso, Diego A. Moreno-Galván, Fernando Sánchez-Vega, A. Pastor López-Monroy, Petr Motlicek, Esaú Villatoro-Tello

Automatic depression detection from doctor-patient conversations has gained momentum thanks to the availability of public corpora and advances in language modeling. However, interpretability remains limited: strong performance is often reported without revealing what drives predictions. We analyze three datasets: ANDROIDS, DAIC-WOZ, E-DAIC and identify a systematic bias from interviewer prompts in semi-structured interviews. Models trained on interviewer turns exploit fixed prompts and positions to distinguish depressed from control subjects, often achieving high classification scores without using participant language. Restricting models to participant utterances distributes decision evidence more broadly and reflects genuine linguistic cues. While semi-structured protocols ensure consistency, including interviewer prompts inflates performance by leveraging script artifacts. Our results highlight a cross-dataset, architecture-agnostic bias and emphasize the need for analyses that localize decision evidence by time and speaker to ensure models learn from participants' language.

comment: Accepted to LREC 2026 Conference

☆ HASS: Hierarchical Simulation of Logopenic Aphasic Speech for Scalable PPA Detection

Harrison Li, Kevin Wang, Cheol Jun Cho, Jiachen Lian, Rabab Rangwala, Chenxu Guo, Emma Yang, Lynn Kurteff, Zoe Ezzes, Willa Keegan-Rodewald, Jet Vonk, Siddarth Ramkrishnan, Giada Antonicelli, Zachary Miller, Marilu Gorno Tempini, Gopala Anumanchipalli

Building a diagnosis model for primary progressive aphasia (PPA) has been challenging due to the data scarcity. Collecting clinical data at scale is limited by the high vulnerability of clinical population and the high cost of expert labeling. To circumvent this, previous studies simulate dysfluent speech to generate training data. However, those approaches are not comprehensive enough to simulate PPA as holistic, multi-level phenotypes, instead relying on isolated dysfluencies. To address this, we propose a novel, clinically grounded simulation framework, Hierarchical Aphasic Speech Simulation (HASS). HASS aims to simulate behaviors of logopenic variant of PPA (lvPPA) with varying degrees of severity. To this end, semantic, phonological, and temporal deficits of lvPPA are systematically identified by clinical experts, and simulated. We demonstrate that our framework enables more accurate and generalizable detection models.

♻ ☆ DELULU: Discriminative Embedding Learning Using Latent Units for Speaker-Aware Self-Trained Speech Foundational Model

Massa Baali, Rita Singh, Bhiksha Raj

Self-supervised speech models have achieved remarkable success on content-driven tasks, yet they remain limited in capturing speaker-discriminative features critical for verification, diarization, and profiling applications. We introduce \textsc{DELULU}, a speaker-aware self-trained foundational model that addresses this limitation by incorporating speaker-informed structure into pseudo-label generation. DELULU leverages frame-level embeddings from ReDimNet, a state-of-the-art speaker verification model, to guide k-means clustering during pre-training, introducing a speaker-discriminative inductive bias that aligns representation learning with speaker identity. DELULU significantly outperforms prior SSL models across a range of speaker-centric tasks, achieving up to \textbf{62\% relative improvement} in equal error rate (EER) for speaker verification and consistent gains on zero-shot profiling tasks including gender, age, accent, and speaker counting; notably surpassing even its teacher model on zero-shot evaluations. Our findings demonstrate that \textbf{DELULU is a strong universal encoder for speaker-aware speech processing}, enabling superior performance without task-specific fine-tuning.

♻ ☆ An interpretable speech foundation model for depression detection by revealing prediction-relevant acoustic features from long speech

Qingkun Deng, Saturnino Luz, Sofia de la Fuente Garcia

Speech-based depression detection tools could aid early screening. Here, we propose an interpretable speech foundation model approach to enhance the clinical applicability of such tools. We introduce a speech-level Audio Spectrogram Transformer (AST) to detect depression using long-duration speech instead of short segments, along with a novel interpretation method that reveals prediction-relevant acoustic features for clinician interpretation. Our experiments show the proposed model outperforms a segment-level AST, highlighting the impact of segment-level labelling noise and the advantage of leveraging longer speech duration for more reliable depression detection. Through interpretation, we observe our model identifies reduced loudness and F0 as relevant depression signals, aligning with documented clinical findings. This interpretability supports a responsible AI approach for speech-based depression detection, rendering such tools more clinically applicable.

comment: 5 pages, 3 figures. arXiv admin note: substantial text overlap with arXiv:2309.13476

♻ ☆ OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model

Maomao Li, Zhen Li, Kaipeng Zhang, Guosheng Yin, Zhifeng Li, Dong Xu

Existing mainstream video customization methods focus on generating identity-consistent videos based on given reference images and textual prompts. Benefiting from the rapid advancement of joint audio-video generation, this paper proposes a more compelling new task: sync audio-video customization, which aims to synchronously customize both video identity and audio timbre. Specifically, given a reference image $I^{r}$ and a reference audio $A^{r}$, this novel task requires generating videos that maintain the identity of the reference image while imitating the timbre of the reference audio, with spoken content freely specifiable through user-provided textual prompts. To this end, we propose OmniCustom, a powerful DiT-based audio-video customization framework that can synthesize a video following reference image identity, audio timbre, and text prompts all at once in a zero-shot manner. Our framework is built on three key contributions. First, identity and audio timbre control are achieved through separate reference identity and audio LoRA modules that operate through self-attention layers within the base audio-video generation model. Second, we introduce a contrastive learning objective alongside the standard flow matching objective. It uses predicted flows conditioned on reference inputs as positive examples and those without reference conditions as negative examples, thereby enhancing the model ability to preserve identity and timbre. Third, we train OmniCustom on our constructed large-scale, high-quality audio-visual human dataset. Extensive experiments demonstrate that OmniCustom outperforms existing methods in generating audio-video content with consistent identity and timbre fidelity. Project page: https://omnicustom-project.github.io/page/.

comment: code: https://github.com/OmniCustom-project/OmniCustom

Audio and Speech Processing 13

☆ YingMusic-Singer: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance

Chunbo Hao, Junjie Zheng, Guobin Ma, Yuepeng Jiang, Huakang Chen, Wenjie Tian, Gongyu Chen, Zihao Chen, Lei Xie

☆ ArrayDPS-Refine: Generative Refinement of Discriminative Multi-Channel Speech Enhancement ICASSP 2026

Zhongweiyang Xu, Ashutosh Pandey, Juan Azcarreta, Zhaoheng Ni, Sanjeel Parekh, Buye Xu

Multi-channel speech enhancement aims to recover clean speech from noisy multi-channel recordings. Most deep learning methods employ discriminative training, which can lead to non-linear distortions from regression-based objectives, especially under challenging environmental noise conditions. Inspired by ArrayDPS for unsupervised multi-channel source separation, we introduce ArrayDPS-Refine, a method designed to enhance the outputs of discriminative models using a clean speech diffusion prior. ArrayDPS-Refine is training-free, generative, and array-agnostic. It first estimates the noise spatial covariance matrix (SCM) from the enhanced speech produced by a discriminative model, then uses this estimated noise SCM for diffusion posterior sampling. This approach allows direct refinement of any discriminative model's output without retraining. Our results show that ArrayDPS-Refine consistently improves the performance of various discriminative models, including state-of-the-art waveform and STFT domain models. Audio demos are provided at https://xzwy.github.io/ArrayDPSRefineDemo/.

comment: Accepted to ICASSP 2026

☆ Semantic-Aware Interruption Detection in Spoken Dialogue Systems: Benchmark, Metric, and Model ICME 2026

Kangxiang Xia, Bingshen Mu, Xian Shi, Jin Xu, Lei Xie

comment: Accepted by ICME 2026

☆ How Open is Open TTS? A Practical Evaluation of Open Source TTS Tools for Romanian

Teodora Răgman, Adrian Bogdan Stânea, Horia Cucu, Adriana Stan

comment: Published in IEEE Access

☆ Photogrammetry-Reconstructed 3D Head Meshes for Accessible Individual Head-Related Transfer Functions

Ludovic Pirard, Lorenzo Picinali, Katarina C. Poole

Individual head-related transfer functions (HRTFs) are essential for accurate spatial audio binaural rendering but remain difficult to obtain due to measurement complexity. This study investigates whether photogrammetry-reconstructed (PR) head and ear meshes, acquired with consumer hardware, can provide a practically useful baseline for individual HRTF synthesis. Using the SONICOM HRTF dataset, 72-image photogrammetry captures per subject were processed with Apple's Object Capture API to generate PR meshes for 150 subjects. Mesh2HRTF was used to compute PR synthetic HRTFs, which were compared against measured HRTFs, high-resolution 3D scan-derived HRTFs, KEMAR, and random HRTFs through numerical evaluation, auditory models, and a behavioural sound localisation experiment (N = 27). PR synthetic HRTFs preserved ITD cues but exhibited increased ILD and spectral errors. Auditory-model predictions and behavioural data showed substantially higher quadrant error rates, reduced elevation accuracy, and greater front-back confusions than measured HRTFs, performing worse than random HRTFs on perceptual metrics. Current photogrammetry pipelines support individual HRTF synthesis but are limited by insufficient pinna morphology details and high-frequency spectral fidelity needed for accurate individual HRTFs containing monaural cues.

comment: Submitted to Acta Acustica Topical Issue - Spatial and binaural hearing: From neural processes to applications

☆ ACAVCaps: Enabling large-scale training for fine-grained and diverse audio understanding ICASSP 2026

Yadong Niu, Tianzi Wang, Heinrich Dinkel, Xingwei Sun, Jiahao Zhou, Gang Li, Jizhong Liu, Junbo Zhang, Jian Luan

comment: accepted by ICASSP 2026

☆ Rethinking Masking Strategies for Masked Prediction-based Audio Self-supervised Learning IJCNN 2026

Daisuke Niizumi, Daiki Takeuchi, Masahiro Yasuda, Binh Thien Nguyen, Noboru Harada, Nobutaka Ono

comment: 6+1 pages, 2 figures, 3 tables, accepted at IJCNN 2026

☆ Unified Diffusion Refinement for Multi-Channel Speech Enhancement and Separation

Zhongweiyang Xu, Ashutosh Pandey, Juan Azcarreta, Zhaoheng Ni, Sanjeel Parekh, Buye Xu, Romit Roy Choudhury

We propose Uni-ArrayDPS, a novel diffusion-based refinement framework for unified multi-channel speech enhancement and separation. Existing methods for multi-channel speech enhancement/separation are mostly discriminative and are highly effective at producing high-SNR outputs. However, they can still generate unnatural speech with non-linear distortions caused by the neural network and regression-based objectives. To address this issue, we propose Uni-ArrayDPS, which refines the outputs of any strong discriminative model using a speech diffusion prior. Uni-ArrayDPS is generative, array-agnostic, and training-free, and supports both enhancement and separation. Given a discriminative model's enhanced/separated speech, we use it, together with the noisy mixtures, to estimate the noise spatial covariance matrix (SCM). We then use this SCM to compute the likelihood required for diffusion posterior sampling of the clean speech source(s). Uni-ArrayDPS requires only a pre-trained clean-speech diffusion model as a prior and does not require additional training or fine-tuning, allowing it to generalize directly across tasks (enhancement/separation), microphone array geometries, and discriminative model backbones. Extensive experiments show that Uni-ArrayDPS consistently improves a wide range of discriminative models for both enhancement and separation tasks. We also report strong results on a real-world dataset. Audio demos are provided at \href{https://xzwy.github.io/Uni-ArrayDPS/}{https://xzwy.github.io/Uni-ArrayDPS/}.

comment: Paper in submission

☆ When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews LREC 2026

Hasindri Watawana, Sergio Burdisso, Diego A. Moreno-Galván, Fernando Sánchez-Vega, A. Pastor López-Monroy, Petr Motlicek, Esaú Villatoro-Tello

comment: Accepted to LREC 2026 Conference

☆ HASS: Hierarchical Simulation of Logopenic Aphasic Speech for Scalable PPA Detection

♻ ☆ An interpretable speech foundation model for depression detection by revealing prediction-relevant acoustic features from long speech

Qingkun Deng, Saturnino Luz, Sofia de la Fuente Garcia

comment: 5 pages, 3 figures. arXiv admin note: substantial text overlap with arXiv:2309.13476

♻ ☆ OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model

Maomao Li, Zhen Li, Kaipeng Zhang, Guosheng Yin, Zhifeng Li, Dong Xu

comment: code: https://github.com/OmniCustom-project/OmniCustom

♻ ☆ Adaptive Federated Fine-Tuning of Self-Supervised Speech Representations

Xin Guo, Chunrui Zhao, Hong Jia, Ting Dang, Gongping Huang, Xianrui Zheng, Yan Gao

Integrating Federated Learning (FL) with self-supervised learning (SSL) enables privacy-preserving fine-tuning for speech tasks. However, federated environments exhibit significant heterogeneity: clients differ in computational capacity, causing straggler effects under unified fine-tuning, while diverse downstream tasks require different representation depths, making full-model updates inefficient. To address these challenges, we propose an adaptive federated fine-tuning framework with early exits. Lightweight prediction heads are inserted at intermediate layers of the SSL backbone, allowing clients to terminate computation based on local constraints and task requirements. We further introduce a layer-wise, depth-aware partial aggregation strategy to better utilize representations from different network depths. Experiments show that the framework reduces edge overhead, supports heterogeneous hardware, and maintains competitive performance in resource-constrained federated environments.

comment: Submitted to Interspeech 2026

2026-03-24

Sound 14

☆ MSR-HuBERT: Self-supervised Pre-training for Adaptation to Multiple Sampling Rates

Zikang Huang, Meng Ge, Tianrui Wang, Xuanchen Li, Xiaobao Wang, Longbiao Wang, Jianwu Dang

Self-supervised learning (SSL) has advanced speech processing. However, existing speech SSL methods typically assume a single sampling rate and struggle with mixed-rate data due to temporal resolution mismatch. To address this limitation, we propose MSRHuBERT, a multi-sampling-rate adaptive pre-training method. Building on HuBERT, we replace its single-rate downsampling CNN with a multi-sampling-rate adaptive downsampling CNN that maps raw waveforms from different sampling rates to a shared temporal resolution without resampling. This design enables unified mixed-rate pre-training and fine-tuning. In experiments spanning 16 to 48 kHz, MSRHuBERT outperforms HuBERT on speech recognition and full-band speech reconstruction, preserving high-frequency detail while modeling low-frequency semantic structure. Moreover, MSRHuBERT retains HuBERT's mask-prediction objective and Transformer encoder, so existing analyses and improvements that were developed for HuBERT can apply directly.

☆ The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models

Heinrich Dinkel, Jiahao Zhou, Guanbo Wang, Yadong Niu, Junbo Zhang, Yufeng Hao, Ying Liu, Ke Li, Wenwu Wang, Zhiyong Wu, Jian Luan

This paper presents the Interspeech 2026 Audio Encoder Capability Challenge, a benchmark specifically designed to evaluate and advance the performance of pre-trained audio encoders as front-end modules for Large Audio Language Models (LALMs). While LALMs have shown remarkable understanding of complex acoustic scenes, their performance depends on the semantic richness of the underlying audio encoder representations. This challenge addresses the integration gap by providing a unified generative evaluation framework, XARES-LLM, which assesses submitted encoders across a diverse suite of downstream classification and generation tasks. By decoupling encoder development from LLM fine-tuning, the challenge establishes a standardized protocol for general-purpose audio representations that can effectively be used for the next generation of multimodal language models.

comment: Interspeech 2026 Challenge

☆ MuQ-Eval: An Open-Source Per-Sample Quality Metric for AI Music Generation Evaluation

Di Zhu, Zixuan Li

Distributional metrics such as Fréchet Audio Distance cannot score individual music clips and correlate poorly with human judgments, while the only per-sample learned metric achieving high human correlation is closed-source. We introduce MUQ-EVAL, an open-source per-sample quality metric for AIgenerated music built by training lightweight prediction heads on frozen MuQ-310M features using MusicEval, a dataset of generated clips from 31 text-to-music systems with expert quality ratings. Our simplest model, frozen features with attention pooling and a two-layer MLP, achieves system-level SRCC = 0.957 and utterance-level SRCC = 0.838 with human mean opinion scores. A systematic ablation over training objectives and adaptation strategies shows that no addition meaningfully improves the frozen baseline, indicating that frozen MuQ representations already capture quality-relevant information. Encoder choice is the dominant design factor, outweighing all architectural and training decisions. LoRA-adapted models trained on as few as 150 clips already achieve usable correlation, enabling personalized quality evaluators from individual listener annotations. A controlled degradation analysis reveals selective sensitivity to signal-level artifacts but insensitivity to musical-structural distortions. Our metric, MUQ-EVAL, is fully open-source, outperforms existing open per-sample metrics, and runs in real time on a single consumer GPU. Code, model weights, and evaluation scripts are available at https://github.com/dgtql/MuQ-Eval.

comment: 10 Pages, 6 figures

☆ Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers

Jakob Kienegger, Timo Gerkmann

Deep spatially selective filters achieve high-quality enhancement with real-time capable architectures for stationary speakers of known directions. To retain this level of performance in dynamic scenarios when only the speakers' initial directions are given, accurate, yet computationally lightweight tracking algorithms become necessary. Assuming a frame-wise causal processing style, temporal feedback allows for leveraging the enhanced speech signal to improve tracking performance. In this work, we investigate strategies to incorporate the enhanced signal into lightweight tracking algorithms and autoregressively guide deep spatial filters. Our proposed Bayesian tracking algorithms are compatible with arbitrary deep spatial filters. To increase the realism of simulated trajectories during development and evaluation, we propose and publish a novel dataset based on the social force model. Results validate that the autoregressive incorporation significantly improves the accuracy of our Bayesian trackers, resulting in superior enhancement with none or only negligibly increased computational overhead. Real-world recordings complement these findings and demonstrate the generalizability of our methods to unseen, challenging acoustic conditions.

comment: This work has been submitted to the IEEE for possible publication

☆ Crab: Multi Layer Contrastive Supervision to Improve Speech Emotion Recognition Under Both Acted and Natural Speech Condition

Lucas H. Ueda, João G. T. Lima, Paula D. P. Costa

Speech Emotion Recognition (SER) in real-world scenarios remains challenging due to severe class imbalance and the prevalence of spontaneous, natural speech. While recent approaches leverage self-supervised learning (SSL) representations and multimodal fusion of speech and text, most existing methods apply supervision only at the final classification layer, limiting the discriminative power of intermediate representations. In this work, we propose Crab (Contrastive Representation and Multimodal Aligned Bottleneck), a bimodal Cross-Modal Transformer architecture that integrates speech representations from WavLM and textual representations from RoBERTa, together with a novel \textit{Multi Layer Contrastive Supervision} (MLCS) strategy. MLCS injects multi-positive contrastive learning signals at multiple layers of the network, encouraging emotionally discriminative representations throughout the model without introducing additional parameters at inference time. To further address data imbalance, we adopt weighted cross-entropy during training. We evaluate the proposed approach on three benchmark datasets covering different degrees of emotional naturalness: IEMOCAP, MELD, and MSP-Podcast 2.0. Experimental results demonstrate that Crab consistently outperforms strong unimodal and multimodal baselines across all datasets, with particularly large gains under naturalistic and highly imbalanced conditions. These findings highlight the effectiveness of \textit{Multi Layer Contrastive Supervision} as a general and robust strategy for SER. Official implementation can be found in https://github.com/AI-Unicamp/Crab.

comment: IEEE Transactions on Affective Computing submission

☆ Echoes: A semantically-aligned music deepfake detection dataset

Octavian Pascu, Dan Oneata, Horia Cucu, Nicolas M. Muller

We introduce Echoes, a new dataset for music deepfake detection designed for training and benchmarking detectors under realistic and provider-diverse conditions. Echoes comprises 3,577 tracks (110 hours of audio) spanning multiple genres (pop, rock, electronic), and includes content generated by ten popular AI music generation systems. To prevent shortcut learning and promote robust generalization, the dataset is deliberately constructed to be challenging, enforcing semantic-level alignment between spoofed audio and bona fide references. This alignment is achieved by conditioning generated audio samples directly on bona-fide waveforms or song descriptors. We evaluate Echoes in a cross-dataset setting against three existing AI-generated music datasets using state-of-the-art Wav2Vec2 XLS-R 2B representations. Results show that (i) Echoes is the hardest in-domain dataset; (ii) detectors trained on existing datasets transfer poorly to Echoes; (iii) training on Echoes yields the strongest generalization performance. These findings suggest that provider diversity and semantic alignment help learn more transferable detection cues.

♻ ☆ Do Modern Video-LLMs Need to Listen? A Benchmark Audit and Scalable Remedy

Geewook Kim, Minjoon Seo

Speech and audio encoders developed over years of community effort are routinely excluded from video understanding pipelines -- not because they fail, but because benchmarks never required listening. We audit 10 video benchmarks and find items largely solvable from visual cues alone: a single-frame probe answers ~76% of AVQA without audio, suggesting poor measurement of audio-visual reasoning. Building on LLaVA-OneVision, we attach a speech/audio encoder and compare five compressor architectures under 25x token reduction (25 Hz to 1 Hz). Across 10 benchmarks -- with and without filtering -- audio yields clear gains on tasks requiring speech comprehension or cross-modal grounding, while vision-centric suites remain largely unaffected. Our results show that speech encoders play a larger role in video understanding than current benchmarks suggest. We will fully open-source our work at https://github.com/naver-ai/LLaVA-AV-SSM.

comment: Submitted to Interspeech 2026

♻ ☆ DreamAudio: Customized Text-to-Audio Generation with Diffusion Models

Yi Yuan, Xubo Liu, Haohe Liu, Xiyuan Kang, Zhuo Chen, Yuxuan Wang, Mark D. Plumbley, Wenwu Wang

With the development of large-scale diffusion-based and language-modeling-based generative models, impressive progress has been achieved in text-to-audio generation. Despite producing high-quality outputs, existing text-to-audio models mainly aim to generate semantically aligned sound and fall short of controlling fine-grained acoustic characteristics of specific sounds. As a result, users who need specific sound content may find it difficult to generate the desired audio clips. In this paper, we present DreamAudio for customized text-to-audio generation (CTTA). Specifically, we introduce a new framework that is designed to enable the model to identify auditory information from user-provided reference concepts for audio generation. Given a few reference audio samples containing personalized audio events, our system can generate new audio samples that include these specific events. In addition, two types of datasets are developed for training and testing the proposed systems. The experiments show that DreamAudio generates audio samples that are highly consistent with the customized audio features and aligned well with the input text prompts. Furthermore, DreamAudio offers comparable performance in general text-to-audio tasks. We also provide a human-involved dataset containing audio events from real-world CTTA cases as the benchmark for customized generation tasks.

comment: Accepted by IEEE/ACM Transactions on Audio, Speech, and Language Processing. Demos are available at https://yyua8222.github.io/DreamAudio_demopage/

♻ ☆ Investigating self-supervised representations for audio-visual deepfake detection CVPR

Dragos-Alexandru Boldisor, Stefan Smeu, Dan Oneata, Elisabeta Oneata

Self-supervised representations excel at many vision and speech tasks, but their potential for audio-visual deepfake detection remains underexplored. Unlike prior work that uses these features in isolation or buried within complex architectures, we systematically evaluate them across modalities (audio, video, multimodal) and domains (lip movements, generic visual content). We assess three key dimensions: detection effectiveness, interpretability of encoded information, and cross-modal complementarity. We find that most self-supervised features capture deepfake-relevant information, and that this information is complementary. Moreover, models primarily attend to semantically meaningful regions rather than spurious artifacts (such as the leading silence). Among the investigated features, audio-informed representations generalize best and achieve state-of-the-art results. However, generalization to realistic in-the-wild data remains challenging. Our analysis indicates this gap stems from intrinsic dataset difficulty rather than from features latching onto superficial patterns. Project webpage: https://bit-ml.github.io/ssr-dfd.

comment: Accepted to the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026

♻ ☆ Voice Privacy from an Attribute-based Perspective

Mehtab Ur Rahman, Martha Larson, Cristian Tejedor-Garcia

Voice privacy approaches that preserve the anonymity of speakers modify speech in an attempt to break the link with the true identity of the speaker. Current benchmarks measure speaker protection based on signal-to-signal comparisons. In this paper, we introduce an attribute-based perspective, where we measure privacy protection in terms of comparisons between sets of speaker attributes. First, we analyze privacy impact by calculating speaker uniqueness for ground truth attributes, attributes inferred on the original speech, and attributes inferred on speech protected with standard anonymization. Next, we examine a threat scenario involving only a single utterance per speaker and calculate attack error rates. Overall, we observe that inferred attributes still present a risk despite attribute inference errors. Our research points to the importance of considering both attribute-related threats and protection mechanisms in future voice privacy research.

comment: Submitted to InterSpeech 2026. Author name corrected

♻ ☆ ASK: Adaptive Self-improving Knowledge Framework for Audio Text Retrieval

Siyuan Fu, Xuchen Guo, Mingjun Liu, Hongxiang Li, Boyin Tan, Gongxi Zhu, Xianwei Zhuang, Jinghan Ru, Yuxin Xie, Yuguo Yin

The dominant paradigm for Audio-Text Retrieval (ATR) relies on dual-encoder architectures optimized via mini-batch contrastive learning. However, restricting optimization to local in-batch samples creates a fundamental limitation we term the Gradient Locality Bottleneck (GLB), which prevents the resolution of acoustic ambiguities and hinders the learning of rare long-tail concepts. While external knowledge injection can break this bottleneck, it often triggers a problem called Representation-Drift Mismatch (RDM), where a static knowledge base becomes misaligned with evolving encoders, degrading guidance into noise. To address these intertwined challenges, we propose the Adaptive Self-improving Knowledge (ASK) framework. ASK breaks the GLB via multi-grained knowledge injection and mitigates RDM through a dynamic refinement strategy that synchronizes the knowledge base with the model. Additionally, an adaptive reliability weighting scheme is employed to filter retrieval noise based on cross-modal consistency. Extensive experiments across multiple benchmarks demonstrate that ASK consistently achieves new state-of-the-art performance across various backbones.

♻ ☆ U3-xi: Pushing the Boundaries of Speaker Recognition by Incorporating Uncertainty

Junjie Li, Kong Aik Lee

An utterance-level speaker embedding is typically obtained by aggregating a sequence of frame-level representations. However, in real-world scenarios, individual frames encode not only speaker-relevant information but also various nuisance factors. As a result, different frames contribute unequally to the final utterance-level speaker representation for Automatic Speaker Verification systems. To address this issue, we propose to estimate the inherent uncertainty of each frame and assign adaptive weights accordingly, where frames with higher uncertainty receive lower attention. Based on this idea, we present U3-xi, a comprehensive framework designed to produce more reliable and interpretable uncertainty estimates for speaker embeddings. Specifically, we introduce several strategies for uncertainty supervision. First, we propose speaker-level uncertainty supervision via a Stochastic Variance Loss, where the distance between an utterance embedding and its corresponding speaker centroid serves as a pseudo ground truth for uncertainty learning. Second, we incorporate global-level uncertainty supervision by injecting the predicted uncertainty into the sof tmax scale during training. This adaptive scaling mechanism adjusts the sharpness of the decision boundary according to sample difficulty, providing global guidance. Third, we redesign the uncertainty estimation module by integrating a Transformer encoder with multi-view self-attention, enabling the model to capture rich local and long-range temporal dependencies. Comprehensive experiments demonstrate that U3-xi is model-agnostic and can be seamlessly applied to various speaker encoders. In particular, when applied to ECAPA-TDNN, it achieves 21.1% and 15.57% relative improvements on the VoxCeleb1 test sets in terms of EER and minDCF, respectively.

♻ ☆ Adapting Self-Supervised Speech Representations for Cross-lingual Dysarthria Detection in Parkinson's Disease

Abner Hernandez, Eunjung Yeo, Kwanghee Choi, Chin-Jou Li, Zhengjun Yue, Rohan Kumar Das, Jan Rusz, Mathew Magimai Doss, Juan Rafael Orozco-Arroyave, Tomás Arias-Vergara, Andreas Maier, Elmar Nöth, David R. Mortensen, David Harwath, Paula Andrea Perez-Toro

The limited availability of dysarthric speech data makes cross-lingual detection an important but challenging problem. A key difficulty is that speech representations often encode language-dependent structure that can confound dysarthria detection. We propose a representation-level language shift (LS) that aligns source-language self-supervised speech representations with the target-language distribution using centroid-based vector adaptation estimated from healthy-control speech. We evaluate the approach on oral DDK recordings from Parkinson's disease speech datasets in Czech, German, and Spanish under both cross-lingual and multilingual settings. LS substantially improves sensitivity and F1 in cross-lingual settings, while yielding smaller but consistent gains in multilingual settings. Representation analysis further shows that LS reduces language identity in the embedding space, supporting the interpretation that LS removes language-dependent structure.

comment: Submitted to Interspeech 2026

♻ ☆ Selective Classifier-free Guidance for Zero-shot Text-to-speech ICASSP

John Zheng, Farhad Maleki

In zero-shot text-to-speech, achieving a balance between fidelity to the target speaker and adherence to text content remains a challenge. While classifier-free guidance (CFG) strategies have shown promising results in image generation, their application to speech synthesis are underexplored. Separating the conditions used for CFG enables trade-offs between different desired characteristics in speech synthesis. In this paper, we evaluate the adaptability of CFG strategies originally developed for image generation to speech synthesis and extend separated-condition CFG approaches for this domain. Our results show that CFG strategies effective in image generation generally fail to improve speech synthesis. We also find that we can improve speaker similarity while limiting degradation of text adherence by applying standard CFG during early timesteps and switching to selective CFG only in later timesteps. Surprisingly, we observe that the effectiveness of a selective CFG strategy is highly text-representation dependent, as differences between the two languages of English and Mandarin can lead to different results even with the same model.

comment: 5 pages, 7 figures, 1 table. Revision 1: removed ICASSP copyright notice

Audio and Speech Processing 13

☆ Prompt Amplification and Zero-Shot Late Fusion in Audio-Language Models for Speech Emotion Recognition

Saurabh Kataria, Xiao Hu

Audio-Language Models (ALMs) are making strides in understanding speech and non-speech audio. However, domain-specialist Foundation Models (FMs) remain the best for closed-ended speech processing tasks such as Speech Emotion Recognition (SER). Using ALMs for Zero-shot SER is a popular choice, but their potential to work with specialists to achieve state-of-the-art (SOTA) performance remains unexplored. We propose ZS-Fuse, a late-fusion method that combines zero-shot emotion estimates from a dual-encoder ALM with specialist FMs. To handle ambiguity in emotions and sensitivity to prompt choice, 1) we use a simple prompt ensemble and 2) suggest a novel technique called prompt amplification, which repeats audio and text queries to discover stronger zero-shot capabilities. We demonstrate the efficacy of our technique by evaluating ZS-Fuse with three dual-encoder ALMs and two FMs, and report improvements over SOTA baselines, such as WavLM-Large, on three speech emotion recognition datasets.

☆ Modelling Emotions is an Elusive Pursuit in Affective Computing

Anders Rolighed Larsen, Sneha Das, Line Clemmensen

Affective computing - combining sensor technology, machine learning, and psychology - have been studied for over three decades and is employed in AI-powered technologies to enhance emotional awareness in AI systems, and detect symptoms of mental health disorders such as anxiety and depression. However, the uncertainty in such systems remains high, and the application areas are limited by categorical definitions of emotions and emotional concepts. This paper argues that categorical emotion labels obscure emotional nuance in affective computing, and therefore continuous dimensional definitions are needed to advance the field, increase application usefulness, and lower uncertainties.

☆ The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models

Heinrich Dinkel, Jiahao Zhou, Guanbo Wang, Yadong Niu, Junbo Zhang, Yufeng Hao, Ying Liu, Ke Li, Wenwu Wang, Zhiyong Wu, Jian Luan

comment: Interspeech 2026 Challenge

☆ Who Spoke What When? Evaluating Spoken Language Models for Conversational ASR with Semantic and Overlap-Aware Metrics INTERSPEECH 2026

Naohiro Tawara, Samuele Cornell, Alexander Polok, Marc Delcroix, Lukáš Burget, Shinji Watanabe

Conversational automatic speech recognition remains challenging due to overlapping speech, far-field noise, and varying speaker counts. While recent LLM-based systems perform well on single-speaker benchmarks, their robustness in multi-speaker settings is unclear. We systematically compare LLM-based and modular pipeline approaches along four axes: overlap robustness, semantic fidelity, speaker count, and single- versus multi-channel input. To capture meaning-altering errors that conventional metrics miss, we introduce tcpSemER, which extends tcpWER by replacing Levenshtein distance with embedding-based semantic similarity. We further decompose tcpWER into overlapping and non-overlapping components for finer-grained analysis. Experiments across three datasets show that LLM-based systems are competitive in two-speaker settings but degrade as speaker count and overlap increase, whereas modular pipelines remain more robust.

comment: Submitted to INTERSPEECH 2026

☆ Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers

Jakob Kienegger, Timo Gerkmann

comment: This work has been submitted to the IEEE for possible publication

☆ Crab: Multi Layer Contrastive Supervision to Improve Speech Emotion Recognition Under Both Acted and Natural Speech Condition

Lucas H. Ueda, João G. T. Lima, Paula D. P. Costa

comment: IEEE Transactions on Affective Computing submission

☆ Echoes: A semantically-aligned music deepfake detection dataset

Octavian Pascu, Dan Oneata, Horia Cucu, Nicolas M. Muller

♻ ☆ DreamAudio: Customized Text-to-Audio Generation with Diffusion Models

Yi Yuan, Xubo Liu, Haohe Liu, Xiyuan Kang, Zhuo Chen, Yuxuan Wang, Mark D. Plumbley, Wenwu Wang

comment: Accepted by IEEE/ACM Transactions on Audio, Speech, and Language Processing. Demos are available at https://yyua8222.github.io/DreamAudio_demopage/

♻ ☆ WiRD-Gest: Gesture Recognition In The Real World Using Range-Doppler Wi-Fi Sensing on COTS Hardware

Jessica Sanson, Rahul C. Shah, Yazhou Zhu, Rafael Rosales, Valerio Frascolla

Wi-Fi sensing has emerged as a promising technique for gesture recognition, yet its practical deployment is hindered by environmental sensitivity and device placement challenges. To overcome these limitations we propose Wi-Fi Range and Doppler (WiRD)-Gest, a novel system that performs gesture recognition using a single, unmodified Wi-Fi transceiver on a commercial off-the-shelf (COTS) laptop. The system leverages an monostatic full duplex sensing pipeline capable of extracting Range-Doppler (RD) information. Utilizing this, we present the first benchmark of deep learning models for gesture recognition based on monostatic sensing. The key innovation lies in how monostatic sensing and spatial (range) information fundamentally transforms accuracy, robustness and generalization compared to prior approaches. We demonstrate excellent performance in crowded, unseen public spaces with dynamic interference and additional moving targets even when trained on data from controlled environments only. These are scenarios where prior Wi-Fi sensing approaches often fail, however, our system suffers minor degradation. The WiRD-Gest benchmark and dataset will also be released as open source.

♻ ☆ ASK: Adaptive Self-improving Knowledge Framework for Audio Text Retrieval

Siyuan Fu, Xuchen Guo, Mingjun Liu, Hongxiang Li, Boyin Tan, Gongxi Zhu, Xianwei Zhuang, Jinghan Ru, Yuxin Xie, Yuguo Yin

♻ ☆ Towards Inclusive Communication: A Unified Framework for Generating Spoken Language from Sign, Lip, and Audio

Jeong Hun Yeo, Hyeongseop Rha, Sungjune Park, Junil Won, Yong Man Ro

Audio is the primary modality for human communication and has driven the success of Automatic Speech Recognition (ASR) technologies. However, such audio-centric systems inherently exclude individuals who are deaf or hard of hearing. Visual alternatives such as sign language and lip reading offer effective substitutes, and recent advances in Sign Language Translation (SLT) and Visual Speech Recognition (VSR) have improved audio-less communication. Yet, these modalities have largely been studied in isolation, and their integration within a unified framework remains underexplored. In this paper, we propose the first unified framework capable of handling diverse combinations of sign language, lip movements, and audio for spoken-language text generation. We focus on three main objectives: (i) designing a unified, modality-agnostic architecture capable of effectively processing heterogeneous inputs; (ii) exploring the underexamined synergy among modalities, particularly the role of lip movements as non-manual cues in sign language comprehension; and (iii) achieving performance on par with or superior to state-of-the-art models specialized for individual tasks. Building on this framework, we achieve performance on par with or better than task-specific state-of-the-art models across SLT, VSR, ASR, and Audio-Visual Speech Recognition. Furthermore, our analysis reveals a key linguistic insight: explicitly modeling lip movements as a distinct modality significantly improves SLT performance by capturing critical non-manual cues.

comment: Updated the professional title of the corresponding author. Added an Acknowledgement section

♻ ☆ Selective Classifier-free Guidance for Zero-shot Text-to-speech ICASSP

John Zheng, Farhad Maleki

comment: 5 pages, 7 figures, 1 table. Revision 1: removed ICASSP copyright notice

♻ ☆ Adapting Self-Supervised Speech Representations for Cross-lingual Dysarthria Detection in Parkinson's Disease

comment: Submitted to Interspeech 2026

2026-03-23

Sound 13

☆ SelfTTS: cross-speaker style transfer through explicit embedding disentanglement and self-refinement using self-augmentation

Lucas H. Ueda, João G. T. Lima, Pedro R. Corrêa, Flávio O. Simões, Mário U. Neto, Paula D. P. Costa

This paper presents SelfTTS, a text-to-speech (TTS) model designed for cross-speaker style transfer that eliminates the need for external pre-trained speaker or emotion encoders. The architecture achieves emotional expressivity in neutral speakers through an explicit disentanglement strategy utilizing Gradient Reversal Layers (GRL) combined with cosine similarity loss to decouple speaker and emotion information. We introduce Multi Positive Contrastive Learning (MPCL) to induce clustered representations of speaker and emotion embeddings based on their respective labels. Furthermore, SelfTTS employs a self-refinement strategy via Self-Augmentation, exploiting the model's voice conversion capabilities to enhance the naturalness of synthesized speech. Experimental results demonstrate that SelfTTS achieves superior emotional naturalness (eMOS) and robust stability in target timbre and emotion compared to state-of-the-art baselines.

comment: Submitted to Interspeech 2026

☆ Adapting Self-Supervised Speech Representations for Cross-lingual Dysarthria Detection in Parkinson's Disease

comment: Submitted to Interspeech 2026

☆ AnimalCLAP: Taxonomy-Aware Language-Audio Pretraining for Species Recognition and Trait Inference ICASSP 2026

Risa Shinoda, Kaede Shiohara, Nakamasa Inoue, Hiroaki Santo, Fumio Okura

Animal vocalizations provide crucial insights for wildlife assessment, particularly in complex environments such as forests, aiding species identification and ecological monitoring. Recent advances in deep learning have enabled automatic species classification from their vocalizations. However, classifying species unseen during training remains challenging. To address this limitation, we introduce AnimalCLAP, a taxonomy-aware language-audio framework comprising a new dataset and model that incorporate hierarchical biological information. Specifically, our vocalization dataset consists of 4,225 hours of recordings covering 6,823 species, annotated with 22 ecological traits. The AnimalCLAP model is trained on this dataset to align audio and textual representations using taxonomic structures, improving the recognition of unseen species. We demonstrate that our proposed model effectively infers ecological and biological attributes of species directly from their vocalizations, achieving superior performance compared to CLAP. Our dataset, code, and models will be publicly available at https://dahlian00.github.io/AnimalCLAP_Page/.

comment: ICASSP 2026

☆ Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learning

Xi Xuan, Wenxin Zhang, Zhiyu Li, Jennifer Williams, Ville Hautamäki, Tomi H. Kinnunen

Speech deepfake source verification systems aims to determine whether two synthetic speech utterances originate from the same source generator, often assuming that the resulting source embeddings are independent of speaker traits. However, this assumption remains unverified. In this paper, we first investigate the impact of speaker factors on source verification. We propose a speaker-disentangled metric learning (SDML) framework incorporating two novel loss functions. The first leverages Chebyshev polynomial to mitigate gradient instability during disentanglement optimization. The second projects source and speaker embeddings into hyperbolic space, leveraging Riemannian metric distances to reduce speaker information and learn more discriminative source features. Experimental results on MLAAD benchmark, evaluated under four newly proposed protocols designed for source-speaker disentanglement scenarios, demonstrate the effectiveness of SDML framework. The code, evaluation protocols and demo website are available at https://github.com/xxuan-acoustics/RiemannSD-Net.

comment: Submitted to Interspeech 2026; The code, evaluation protocols and demo website are available at https://github.com/xxuan-acoustics/RiemannSD-Net

☆ LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Signal Processing and its Application to Plug-and-Play Dereverberation ICASSP 2026

Kazuki Matsumoto, Ren Uchida, Kohei Yatabe

The robustness of deep neural networks (DNNs) can be certified through their Lipschitz continuity, which has made the construction of Lipschitz-continuous DNNs an active research field. However, DNNs for audio processing have not been a major focus due to their poor compatibility with existing results. In this paper, we consider the amplitude modifier (AM), a popular architecture for handling audio signals, and propose its Lipschitz-continuous variants, which we refer to as LipsAM. We prove a sufficient condition for an AM to be Lipschitz continuous and propose two architectures as examples of LipsAM. The proposed architectures were applied to a Plug-and-Play algorithm for speech dereverberation, and their improved stability is demonstrated through numerical experiments.

comment: Accepted for IEEE ICASSP 2026

☆ DiT-Flow: Speech Enhancement Robust to Multiple Distortions based on Flow Matching in Latent Space and Diffusion Transformers

Tianyu Cao, Helin Wang, Ari Frummer, Yuval Sieradzki, Adi Arbel, Laureano Moro Velazquez, Jesus Villalba, Oren Gal, Thomas Thebaud, Najim Dehak

Recent advances in generative models, such as diffusion and flow matching, have shown strong performance in audio tasks. However, speech enhancement (SE) models are typically trained on limited datasets and evaluated under narrow conditions, limiting real-world applicability. To address this, we propose DiT-Flow, a flow matching-based SE framework built on the latent Diffusion Transformer (DiT) backbone and trained for robustness across diverse distortions, including noise, reverberation, and compression. DiT-Flow operates on compact variational auto-encoders (VAEs)-derived latent features. We validated our approach on StillSonicSet, a synthetic yet acoustically realistic dataset composed of LibriSpeech, FSD50K, FMA, and 90 Matterport3D scenes. Experiments show that DiT-Flow consistently outperforms state-of-the-art generative SE models, demonstrating the effectiveness of flow matching in multi-condition speech enhancement. Despite ongoing efforts to expand synthetic data realism, a persistent bottleneck in SE is the inevitable mismatch between training and deployment conditions. By integrating LoRA with the MoE framework, we achieve both parameter-efficient and high-performance training for DiT-Flow robust to multiple distortions with using 4.9% percentage of the total parameters to obtain a better performance on five unseen distortions.

☆ Velocity Potential Neural Field for Efficient Ambisonics Impulse Response Modeling ICASSP 2026

Yoshiki Masuyama, Francois G. Germain, Gordon Wichern, Chiori Hori, Jonathan Le Roux

First-order Ambisonics (FOA) is a standard spatial audio format based on spherical harmonic decomposition. Its zeroth- and first-order components capture the sound pressure and particle velocity, respectively. Recently, physics-informed neural networks have been applied to the spatial interpolation of FOA signals, regularizing the network outputs based on soft penalty terms derived from physical principles, e.g., the linearized momentum equation. In this paper, we reformulate the task so that the predicted FOA signal automatically satisfies the linearized momentum equation. Our network approximates a scalar function called velocity potential, rather than the FOA signal itself. Then, the FOA signal can be readily recovered through the partial derivatives of the velocity potential with respect to the network inputs (i.e., time and microphone position) according to physics of sound propagation. By deriving the four channels of FOA from the single-channel velocity potential, the reconstructed signal follows the physical principle at any time and position by construction. Experimental results on room impulse response reconstruction confirm the effectiveness of the proposed framework.

comment: Accepted to ICASSP 2026

☆ MSP-Conversation: A Corpus for Naturalistic, Time-Continuous Emotion Recognition

Luz Martinez-Lucas, Pravin Mote, Abinay Reddy Naini, Mohammed Abdelwahab, Carlos Busso

Affective computing aims to understand and model human emotions for computational systems. Within this field, speech emotion recognition (SER) focuses on predicting emotions conveyed through speech. While early SER systems relied on limited datasets and traditional machine learning models, recent deep learning approaches demand largescale, naturalistic emotional corpora. To address this need, we introduce the MSP-Conversation corpus: a dataset of more than 70 hours of conversational audio with time-continuous emotional annotations and detailed speaker diarizations. The time-continuous annotations capture the dynamic and contextdependent nature of emotional expression. The annotations in the corpus include fine-grained temporal traces of valence, arousal, and dominance. The audio data is sourced from publicly available podcasts and overlaps with a subset of the isolated speaking turns in the MSP-Podcast corpus to facilitate direct comparisons between annotation methods (i.e., in-context versus out-of-context annotations). The paper outlines the development of the corpus, annotation methodology, analyses of the annotations, and baseline SER experiments, establishing the MSP-Conversation corpus as a valuable resource for advancing research in dynamic SER in naturalistic settings.

♻ ☆ Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic AudioLLMs

Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury

Audio large language models (LLMs) enable unified speech understanding and generation, but adapting them to linguistically complex and dialect-rich settings such as Arabic-English remains challenging. We present a controlled study of multi-task instruction tuning for an Arabic-centric audio LLM across generative tasks including ASR and speech and text summarization, and discriminative tasks including dialect and emotion recognition, in a resource-constrained setting. To support end-to-end Arabic speech summarization, we introduce AraMega-SSum, a first speech summarization resource for training and benchmarking Arabic-centric Audio-LLMs. We compare four training strategies (i) Uniform Task Mixing, (ii) Task-Progressive Curriculum (TPC), (iiii) Aligner-Based Diverse Sampling (ADS) for training-time batch construction, and (iv) A two-stage TPC->ADS strategy. Our results show a clear efficiency-robustness trade-off. ADS speeds up early convergence and improves paralinguistic performance, however, it hurts other tasks. A two-stage TPC-> ADS strategy gives the most reliable overall balance across tasks, offering practical guidance for adapting omni audio LLMs to low-resource, dialect-rich environments. We will make AraMega-SSum and all experimental resources publicly available to the community.

comment: Foundation Models, Large Language Models, Native, Speech Models, Arabic

♻ ☆ VorTEX: Various overlap ratio for Target speech EXtraction

Ro-hoon Oh, Jihwan Seol, Bugeun Kim

Target speech extraction (TSE) aims to recover a target speaker's voice from a mixture. While recent text-prompted approaches have shown promise, most approaches assume fully overlapped mixtures, limiting insight into behavior across realistic overlap ratios. We introduce VorTEX (Various overlap ratio for Target speech EXtraction), a text-prompted TSE architecture with a Decoupled Adaptive Multi-branch (DAM) Fusion block that separates primary extraction from auxiliary regularization pathways. To enable controlled analysis, we construct PORTE, a two-speaker dataset spanning overlap ratios from 0% to 100%. We further propose Suppression Ratio on Energy (SuRE), a diagnostic metric that detects suppression behavior not captured by conventional measures. Experiments show that existing models exhibit suppression or residual interference under overlap, whereas VorTEX achieves the highest separation fidelity across 20-100% overlap (e.g., 5.50 dB at 20% and 2.04 dB at 100%) while maintaining zero SuRE, indicating robust extraction without suppression-driven artifacts.

comment: Submitted to InterSpeech 2026 (under review)

♻ ☆ Mathematical Foundations of Polyphonic Music Generation via Structural Inductive Bias

Joonwon Seo

This monograph introduces a novel approach to polyphonic music generation by addressing the "Missing Middle" problem through structural inductive bias. Focusing on Beethoven's piano sonatas as a case study, we empirically verify the independence of pitch and hand attributes using normalized mutual information (NMI=0.167) and propose the Smart Embedding architecture, achieving a 48.30% reduction in parameters. We provide rigorous mathematical proofs using information theory (negligible loss bounded at 0.153 bits), Rademacher complexity (28.09% tighter generalization bound), and category theory to demonstrate improved stability and generalization. Empirical results show a 9.47% reduction in validation loss, confirmed by SVD analysis and an expert listening study (N=53). This dual theoretical and applied framework bridges gaps in AI music generation, offering verifiable insights for mathematically grounded deep learning.

comment: 81 pages. A comprehensive monograph detailing the Smart Embedding architecture for polyphonic music generation, including theoretical proofs (Information Theory, Rademacher Complexity, RPTP) and human evaluation results

♻ ☆ Structural and Statistical Audio Texture Knowledge Distillation for Acoustic Classification

Jarin Ritu, Amirmohammad Mohammadi, Davelle Carreiro, Alexandra Van Dine, Joshua Peeples

While knowledge distillation has shown success in various audio tasks, its application to environmental sound classification often overlooks essential low-level audio texture features needed to capture local patterns in complex acoustic environments. To address this gap, the Structural and Statistical Audio Texture Knowledge Distillation (SSATKD) framework is proposed, which combines high-level contextual information with low-level structural and statistical audio textures extracted from intermediate layers. To evaluate its generalizability across diverse acoustic domains, SSATKD is tested on four datasets within the environmental sound classification domain, including two passive sonar datasets (DeepShip and Vessel Type Underwater Acoustic Data (VTUAD)) and two general environmental sound datasets (Environmental Sound Classification 50 (ESC-50) and Tampere University of Technology (TUT) Acoustic Scenes). Two teacher adaptation strategies are explored: classifier-head-only adaptation and full fine-tuning. The framework is further evaluated using various convolutional and transformer-based teacher models. Experimental results demonstrate consistent accuracy improvements across all datasets and settings, confirming the effectiveness and robustness of SSATKD in real-world sound classification tasks.

comment: 13 pages, 6 figures

♻ ☆ When Audio-LLMs Don't Listen: A Cross-Linguistic Study of Modality Arbitration

Jayadev Billa

When audio and text conflict, speech-enabled language models follow text far more often than they do when arbitrating between two conflicting text sources, even under explicit instructions to trust the audio. We introduce ALME (Audio-LLM Modality Evaluation), a dataset of 57,602 controlled audio-text conflict stimuli across eight languages, together with Text Dominance Ratio (TDR), which measures how often a model follows conflicting text when instructed to follow audio. Gemini 2.0 Flash and GPT-4o show TDR 10--26$\times$ higher than a baseline that replaces audio with its transcript under otherwise identical conditions (Gemini 2.0 Flash: 16.6% vs. 1.6%; GPT-4o: 23.2% vs. 0.9%). These results suggest that text dominance reflects not only information content, but also an asymmetry in arbitration accessibility, i.e., how easily the model can use competing representations at decision time. Framing the transcript as deliberately corrupted reduces TDR by 80%, whereas forcing explicit transcription increases it by 14%. A fine-tuning ablation further suggests that arbitration behavior depends more on LLM reasoning than on the audio input path alone. Across four audio-LLMs, we observe the same qualitative pattern with substantial cross-model and cross-linguistic variation.

comment: 13 pages, 18 tables, 4 figures, benchmark and code at https://github.com/jb1999/alme-benchmark

Audio and Speech Processing 17

☆ TiCo: Time-Controllable Training for Spoken Dialogue Models

Kai-Wei Chang, Wei-Chih Chen, En-Pei Hu, Hung-yi Lee, James Glass

We propose TiCo, a simple post-training method for enabling spoken dialogue models (SDMs) to follow time-constrained instructions and generate responses with controllable duration. This capability is valuable for real-world spoken language systems such as voice assistants and interactive agents, where controlling response duration can improve interaction quality. However, despite their strong ability to generate natural spoken responses, existing models lack time awareness and struggle to follow duration-related instructions (e.g., "Please generate a response lasting about 15 seconds"). Through an empirical evaluation of both open-source and commercial SDMs, we show that they frequently fail to satisfy such time-control requirements. TiCo addresses this limitation by enabling models to estimate elapsed speaking time during generation through Spoken Time Markers (STM) (e.g., <10.6 seconds>). These markers help the model maintain awareness of time and adjust the remaining content to meet the target duration. TiCo is simple and efficient: it requires only a small amount of data and no additional question-answer pairs, relying instead on self-generation and reinforcement learning. Experimental results show that TiCo significantly improves adherence to duration constraints while preserving response quality.

☆ Semi-Blind Channel Estimation and Hybrid Receiver Beamforming in the Tera-Hertz Multi-User Massive MIMO Uplink

Abhisha Garg, Suraj Srivastava, Varsha Dubey, Aditya Jagannatham, Lajos Hanzo

We develop a pragmatic multi-user (MU) massive multiple-input multiple-output (MIMO) channel model tailored to the THz band, encompassing factors such as molecular absorption, reflection losses and multipath diffused ray components. Next, we propose a novel semi-blind based channel state information (CSI) acquisition technique i.e. MU whitening decorrelation semi-blind (MU-WD-SB) that exploits the second order statistics corresponding to the unknown data symbols along with pilot vectors. A constrained Cramer-Rao Lower Bound (C-CRLB) is derived to bound the normalized mean square error (NMSE) performance of the proposed semi-blind learning technique. Our proposed scheme efficiently reduces the training overheads while enhancing the overall accuracy of the channel learning process. Furthermore, a novel hybrid receiver combiner framework is devised for MU THz massive MIMO systems, leveraging multiple measurement vector based sparse Bayesian learning (MMV-SBL) that relies on the estimated CSI acquired through our proposed semi-blind technique relying on low resolution analog-to-digital converters (ADCs). Finally, we propose an optimal hybrid combiner based on MMV-SBL, which directly reduces the MU interference. Extensive simulations are conducted to evaluate the performance gain of the proposed MU-WD-SB scheme over conventional training-based and other semi-blind learning techniques for a practical THz channel obtained from the high-resolution transmission (HITRAN) database. The metrics considered for quantifying the improvements include the NMSE, bit error rate (BER) and spectral-efficiency (SE).

☆ SelfTTS: cross-speaker style transfer through explicit embedding disentanglement and self-refinement using self-augmentation

Lucas H. Ueda, João G. T. Lima, Pedro R. Corrêa, Flávio O. Simões, Mário U. Neto, Paula D. P. Costa

comment: Submitted to Interspeech 2026

☆ WiRD-Gest: Gesture Recognition In The Real World Using Range-Doppler Wi-Fi Sensing on COTS Hardware

Jessica Sanson, Rahul C. Shah, Yazhou Zhu, Rafael Rosales, Valerio Frascolla

☆ Adaptive Federated Fine-Tuning of Self-Supervised Speech Representations

Xin Guo, Chunrui Zhao, Hong Jia, Ting Dang, Gongping Huang, Xianrui Zheng, Yan Gao

comment: Submitted to Interspeech 2026

☆ Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learning

Xi Xuan, Wenxin Zhang, Zhiyu Li, Jennifer Williams, Ville Hautamäki, Tomi H. Kinnunen

comment: Submitted to Interspeech 2026; The code, evaluation protocols and demo website are available at https://github.com/xxuan-acoustics/RiemannSD-Net

☆ DiT-Flow: Speech Enhancement Robust to Multiple Distortions based on Flow Matching in Latent Space and Diffusion Transformers

Tianyu Cao, Helin Wang, Ari Frummer, Yuval Sieradzki, Adi Arbel, Laureano Moro Velazquez, Jesus Villalba, Oren Gal, Thomas Thebaud, Najim Dehak

☆ TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild

Kai-Wei Chang, Yi-Cheng Lin, Huang-Cheng Chou, Wenze Ren, Yu-Han Huang, Yun-Shao Tsai, Chien-Cheng Chen, Yu Tsao, Yuan-Fu Liao, Shrikanth Narayanan, James Glass, Hung-yi Lee

Speech technologies have advanced rapidly and serve diverse populations worldwide. However, many languages remain underrepresented due to limited resources. In this paper, we introduce \textbf{TaigiSpeech}, a real-world speech intent dataset in Taiwanese Taigi (aka Taiwanese Hokkien/Southern Min), which is a low-resource and primarily spoken language. The dataset is collected from older adults, comprising 21 speakers with a total of 3k utterances. It is designed for practical intent detection scenarios, including healthcare and home assistant applications. To address the scarcity of labeled data, we explore two data mining strategies with two levels of supervision: keyword match data mining with LLM pseudo labeling via an intermediate language and an audio-visual framework that leverages multimodal cues with minimal textual supervision. This design enables scalable dataset construction for low-resource and unwritten spoken languages. TaigiSpeech will be released under the CC BY 4.0 license to facilitate broad adoption and research on low-resource and unwritten languages. The project website and the dataset can be found on https://kwchang.org/taigispeech.

comment: submitted to Interspeech 2026

☆ Precision-Varying Prediction (PVP): Robustifying ASR systems against adversarial attacks

Matías Pizarro, Raghavan Narasimhan, Asja Fischer

With the increasing deployment of automated and agentic systems, ensuring the adversarial robustness of automatic speech recognition (ASR) models has become critical. We observe that changing the precision of an ASR model during inference reduces the likelihood of adversarial attacks succeeding. We take advantage of this fact to make the models more robust by simple random sampling of the precision during prediction. Moreover, the insight can be turned into an adversarial example detection strategy by comparing outputs resulting from different precisions and leveraging a simple Gaussian classifier. An experimental analysis demonstrates a significant increase in robustness and competitive detection performance for various ASR models and attack types.

☆ Velocity Potential Neural Field for Efficient Ambisonics Impulse Response Modeling ICASSP 2026

Yoshiki Masuyama, Francois G. Germain, Gordon Wichern, Chiori Hori, Jonathan Le Roux

comment: Accepted to ICASSP 2026

☆ MSP-Conversation: A Corpus for Naturalistic, Time-Continuous Emotion Recognition

Luz Martinez-Lucas, Pravin Mote, Abinay Reddy Naini, Mohammed Abdelwahab, Carlos Busso

♻ ☆ Neural Directional Filtering Using a Compact Microphone Array

Weilong Huang, Srikanth Raj Chetupalli, Mhd Modar Halimeh, Oliver Thiergart, Emanuël A. P. Habets

Beamforming with desired directivity patterns using compact microphone arrays is essential in many audio applications. Directivity patterns achievable using traditional beamformers depend on the number of microphones and the array aperture. Generally, their effectiveness degrades for compact arrays. To overcome these limitations, we propose a neural directional filtering (NDF) approach that leverages deep neural networks to enable sound capture with a predefined directivity pattern. The NDF computes a single-channel complex mask from the microphone array signals, which is then applied to a reference microphone to produce an output that approximates a virtual directional microphone with the desired directivity pattern. We introduce training strategies and propose data-dependent metrics to evaluate the directivity pattern and directivity factor. We show that the proposed method: i) achieves a frequency-invariant directivity pattern even above the spatial aliasing frequency, ii) can approximate diverse and higher-order patterns, iii) can steer the pattern in different directions, and iv) generalizes to unseen conditions. Lastly, experimental comparisons demonstrate superior performance over conventional beamforming and parametric approaches.

♻ ☆ TRI-DEP: A Trimodal Comparative Study for Depression Detection Using Speech, Text, and EEG

Annisaa Fitri Nurfidausi, Eleonora Mancini, Paolo Torroni

Depression is a widespread mental health disorder, yet its automatic detection remains challenging. Prior work has explored unimodal and multimodal approaches, with multimodal systems showing promise by leveraging complementary signals. However, existing studies are limited in scope, lack systematic comparisons of features, and suffer from inconsistent evaluation protocols. We address these gaps by systematically exploring feature representations and modelling strategies across EEG, together with speech and text. We evaluate handcrafted features versus pre-trained embeddings, assess the effectiveness of different neural encoders, compare unimodal, bimodal, and trimodal configurations, and analyse fusion strategies with attention to the role of EEG. Consistent subject-independent splits are applied to ensure robust, reproducible benchmarking. Our results show that (i) the combination of EEG, speech and text modalities enhances multimodal detection, (ii) pretrained embeddings outperform handcrafted features, and (iii) carefully designed trimodal models achieve state-of-the-art performance. Our work lays the groundwork for future research in multimodal depression detection.

♻ ☆ Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic AudioLLMs

Hunzalah Hassan Bhatti, Firoj Alam, Shammur Absar Chowdhury

comment: Foundation Models, Large Language Models, Native, Speech Models, Arabic

♻ ☆ Mathematical Foundations of Polyphonic Music Generation via Structural Inductive Bias

Joonwon Seo

♻ ☆ Structural and Statistical Audio Texture Knowledge Distillation for Acoustic Classification

Jarin Ritu, Amirmohammad Mohammadi, Davelle Carreiro, Alexandra Van Dine, Joshua Peeples

comment: 13 pages, 6 figures

♻ ☆ When Audio-LLMs Don't Listen: A Cross-Linguistic Study of Modality Arbitration

Jayadev Billa

comment: 13 pages, 18 tables, 4 figures, benchmark and code at https://github.com/jb1999/alme-benchmark

2026-03-22

Sound 11

☆ Enterprise Sales Copilot: Enabling Real-Time AI Support with Automatic Information Retrieval in Live Sales Calls

Jielin Qiu, Liangwei Yang, Ming Zhu, Wenting Zhao, Zhiwei Liu, Juntao Tan, Zixiang Chen, Roshan Ram, Akshara Prabhakar, Rithesh Murthy, Shelby Heinecke, Caiming Xiong, Silvio Savarese, Huan Wang

During live sales calls, customers frequently ask detailed product questions that require representatives to manually search internal databases and CRM systems. This process typically takes 25-65 seconds per query, creating awkward pauses that hurt customer experience and reduce sales efficiency. We present SalesCopilot, a real-time AI-powered assistant that eliminates this bottleneck by automatically detecting customer questions, retrieving relevant information from the product database, and displaying concise answers on the representative's dashboard in seconds. The system integrates streaming speech-to-text transcription, large language model (LLM)-based question detection, and retrieval-augmented generation (RAG) over a structured product database into a unified real-time pipeline. We demonstrate SalesCopilot on an insurance sales scenario with 50 products spanning 10 categories (2,490 FAQs, 290 coverage details, and 162 pricing tiers). In our benchmark evaluation, SalesCopilot achieves a measured mean response time of 2.8 seconds with 100% question detection rate, representing a 14xspeedup compared to manual CRM search in an internal study. The system is domain-agnostic and can be adapted to any enterprise sales domain by replacing the product database.

☆ HELIX: Scaling Raw Audio Understanding with Hybrid Mamba-Attention Beyond the Quadratic Limit

Khushiyant, Param Thakkar

Audio representation learning typically evaluates design choices such as input frontend, sequence backbone, and sequence length in isolation. We show that these axes are coupled, and conclusions from one setting often do not transfer to others. We introduce HELIX, a controlled framework comparing pure Mamba, pure attention, and a minimal hybrid with a single attention bottleneck. All models are parameter-matched at about 8.3M parameters to isolate architectural effects. Across six datasets, we find that the preferred input representation depends on the backbone, and that attention hurts performance on short, stationary audio but becomes important at longer sequence lengths. On a 5-minute speaker identification task with 30,000 tokens, pure attention fails with out-of-memory errors, while HELIX closes an 11.5-point gap over pure Mamba.

comment: 10 Pages, 8 Figures

☆ Fusing Memory and Attention: A study on LSTM, Transformer and Hybrid Architectures for Symbolic Music Generation

Soudeep Ghoshal, Sandipan Chakraborty, Pradipto Chowdhury, Himanshu Buckchash

Machine learning techniques, such as Transformers and Long Short-Term Memory (LSTM) networks, play a crucial role in Symbolic Music Generation (SMG). Existing literature indicates a difference between LSTMs and Transformers regarding their ability to model local melodic continuity versus maintaining global structural coherence. However, their specific properties within the context of SMG have not been systematically studied. This paper addresses this gap by providing a fine-grained comparative analysis of LSTMs versus Transformers for SMG, examining local and global properties in detail using 17 musical quality metrics on the Deutschl dataset. We find that LSTM networks excel at capturing local patterns but fail to preserve long-range dependencies, while Transformers model global structure effectively but tend to produce irregular phrasing. Based on this analysis and leveraging their respective strengths, we propose a Hybrid architecture combining a Transformer Encoder with an LSTM Decoder and evaluate it against both baselines. We evaluated 1,000 generated melodies from each of the three architectures on the Deutschl dataset. The results show that the hybrid method achieves better local and global continuity and coherence compared to the baselines. Our work highlights the key characteristics of these models and demonstrates how their properties can be leveraged to design superior models. We also supported the experiments with ablation studies and human perceptual evaluations, which statistically support the findings and provide robust validation for this work.

comment: 20 pages, 6 figures. Published in Expert Systems with Applications (Elsevier), 2026. DOI: https://doi.org/10.1016/j.eswa.2026.131173

☆ Emotion-Aware Quantization for Discrete Speech Representations: An Analysis of Emotion Preservation

Haoguang Zhou, Siyi Wang, Jingyao Wu, James Bailey, Ting Dang

Modern speech systems increasingly use discretized self-supervised speech representations for compression and integration with token-based models, yet their impact on emotional information remains unclear. We study how residual vector quantization (RVQ) reshapes emotional information in discrete speech representations from both representation- and task-level perspectives. Our analysis shows that aggressive compression disproportionately degrades emotion, with uneven loss across emotion classes and model architectures. To address this, we introduce emotion-aware quantization using emotion-specific and emotion-biased codebooks, improving the preservation of both hard and soft emotion perception. We further propose Emo-Q, a lightweight routed quantization method that selects emotion-specialized codebooks, improving emotion recognition performance at lower bitrates. These results highlight the importance of emotion-aware discretization for robust affective speech processing.

☆ Assessing the Ability of Neural TTS Systems to Model Consonant-Induced F0 Perturbation

Tianle Yang, Chengzhe Sun, Phil Rose, Cassandra L. Jacobs, Siwei Lyu

This study proposes a segmental-level prosodic probing framework to evaluate neural TTS models' ability to reproduce consonant-induced f0 perturbation, a fine-grained segmental-prosodic effect that reflects local articulatory mechanisms. We compare synthetic and natural speech realizations for thousands of words, stratified by lexical frequency, using Tacotron 2 and FastSpeech 2 trained on the same speech corpus (LJ Speech). These controlled analyses are then complemented by a large-scale evaluation spanning multiple advanced TTS systems. Results show accurate reproduction for high-frequency words but poor generalization to low-frequency items, suggesting that the examined TTS architectures rely more on lexical-level memorization than on abstract segmental-prosodic encoding. This finding highlights a limitation in such TTS systems' ability to generalize prosodic detail beyond seen data. The proposed probe offers a linguistically informed diagnostic framework that may inform future TTS evaluation methods, and has implications for interpretability and authenticity assessment in synthetic speech.

comment: Accepted for publication in Computer Speech & Language

☆ SqueezeComposer: Temporal Speed-up is A Simple Trick for Long-form Music Composing

Jianyi Chen, Rongxiu Zhong, Shilei Zhang, Kun Qian, Jinglei Liu, Yike Guo, Wei Xue

Composing coherent long-form music remains a significant challenge due to the complexity of modeling long-range dependencies and the prohibitive memory and computational requirements associated with lengthy audio representations. In this work, we propose a simple yet powerful trick: we assume that AI models can understand and generate time-accelerated (speeded-up) audio at rates such as 2x, 4x, or even 8x. By first generating a high-speed version of the music, we greatly reduce the temporal length and resource requirements, making it feasible to handle long-form music that would otherwise exceed memory or computational limits. The generated audio is then restored to its original speed, recovering the full temporal structure. This temporal speed-up and slow-down strategy naturally follows the principle of hierarchical generation from abstract to detailed content, and can be conveniently applied to existing music generation models to enable long-form music generation. We instantiate this idea in SqueezeComposer, a framework that employs diffusion models for generation in the accelerated domain and refinement in the restored domain. We validate the effectiveness of this approach on two tasks: long-form music generation, which evaluates temporal-wise control (including continuation, completion, and generation from scratch), and whole-song singing accompaniment generation, which evaluates track-wise control. Experimental results demonstrate that our simple temporal speed-up trick enables efficient, scalable, and high-quality long-form music generation. Audio samples are available at https://SqueezeComposer.github.io/.

comment: Under Review

☆ ERM-MinMaxGAP: Benchmarking and Mitigating Gender Bias in Multilingual Multimodal Speech-LLM Emotion Recognition

Zi Haur Pang, Xiaoxue Gao, Tatsuya Kawahara, Nancy F. Chen

Speech emotion recognition (SER) systems can exhibit gender-related performance disparities, but how such bias manifests in multilingual speech LLMs across languages and modalities is unclear. We introduce a novel multilingual, multimodal benchmark built on MELD-ST, spanning English, Japanese, and German, to quantify language-specific SER performance and gender gaps. We find bias is strongly language-dependent, and multimodal fusion does not reliably improve fairness. To address these, we propose ERM-MinMaxGAP, a fairness-informed training objective, which augments empirical risk minimization (ERM) with a proposed adaptive fairness weight mechanism and a novel MinMaxGAP regularizer on the maximum male-female loss gap within each language and modality. Building upon the Qwen2-Audio backbone, our ERM-MinMaxGAP approach improves multilingual SER performance by 5.5% and 5.0% while reducing the overall gender bias gap by 0.1% and 1.4% in the unimodal and multimodal settings, respectively.

☆ Relational graph-driven differential denoising and diffusion attention fusion for multimodal conversation emotion recognition

Ying Liu, Yuntao Shou, Wei Ai, Tao Meng, Keqin Li

In real-world scenarios, audio and video signals are often subject to environmental noise and limited acquisition conditions, resulting in extracted features containing excessive noise. Furthermore, there is an imbalance in data quality and information carrying capacity between different modalities. These two issues together lead to information distortion and weight bias during the fusion phase, impairing overall recognition performance. Most existing methods neglect the impact of noisy modalities and rely on implicit weighting to model modality importance, thereby failing to explicitly account for the predominant contribution of the textual modality in emotion understanding. To address these issues, we propose a relation-aware denoising and diffusion attention fusion model for MCER. Specifically, we first design a differential Transformer that explicitly computes the differences between two attention maps, thereby enhancing temporally consistent information while suppressing time-irrelevant noise, which leads to effective denoising in both audio and video modalities. Second, we construct modality-specific and cross-modality relation subgraphs to capture speaker-dependent emotional dependencies, enabling fine-grained modeling of intra- and inter-modal relationships. Finally, we introduce a text-guided cross-modal diffusion mechanism that leverages self-attention to model intra-modal dependencies and adaptively diffuses audiovisual information into the textual stream, ensuring more robust and semantically aligned multimodal fusion.

comment: 19 pages

♻ ☆ CALM: Class-Conditional Sparse Attention Vectors for Large Audio-Language Models

Videet Mehta, Liming Wang, Hilde Kuehne, Rogerio Feris, James R. Glass, M. Jehanzeb Mirza

Large audio-language models (LALMs) exhibit strong zero-shot capabilities in multiple downstream tasks, such as audio question answering (AQA) and abstract reasoning; however, these models still lag behind specialized models for certain discriminative tasks (e.g., audio classification). Recent studies show that sparse subsets of attention heads within an LALM can serve as strong discriminative feature extractors for downstream tasks such as classification via simple voting schemes. However, these methods assign uniform weights to all selected heads, implicitly assuming that each head contributes equally across all semantic categories. In this work, we propose Class-Conditional Sparse Attention Vectors for Large Audio-Language Models, a few-shot classification method that learns class-dependent importance weights over attention heads. This formulation allows individual heads to specialize in distinct semantic categories and to contribute to ensemble predictions proportionally to their estimated reliability. Experiments on multiple few-shot audio and audiovisual classification benchmarks and tasks demonstrate that our method consistently outperforms state-of-the-art uniform voting-based approaches by up to 14.52%, 1.53%, 8.35% absolute gains for audio classification, audio-visual classification, and spoofing detection respectively.

comment: 11 pages, 6 figures

♻ ☆ Preliminary sonification of ENSO using traditional Javanese gamelan scales

Sandy Hardian Susanto Herho, Rusmawan Suwarman, Nurjanna Joko Trilaksono, Iwan Pramesti Anwar, Faiz Rohman Fajary

Sonification -- the mapping of data to non-speech audio -- offers an underexplored channel for representing complex dynamical systems. We treat El Niño-Southern Oscillation (ENSO), a canonical example of low-dimensional climate chaos, as a test case for culturally-situated sonification evaluated through complex systems diagnostics. Using parameter-mapping sonification of the Niño 3.4 sea surface temperature anomaly index (1870--2024), we encode ENSO variability into two traditional Javanese gamelan pentatonic systems (pelog and slendro) across four composition strategies, then analyze the resulting audio as trajectories in a two-dimensional acoustic phase space. Recurrence-based diagnostics, convex hull geometry, and coupling analysis reveal that the sonification pipeline preserves key dynamical signatures: alternating modes produce the highest trajectory recurrence rates, echoing ENSO's quasi-periodicity; layered polyphonic modes explore the broadest phase space regions; and the two scale families induce qualitatively distinct coupling regimes between spectral brightness and energy -- predominantly anti-phase in pelog but near-independent in slendro. Phase space trajectory analysis provides a rigorous geometric framework for comparing sonification designs within a complex systems context. Perceptual validation remains necessary; we contribute the dynamical systems methodology for evaluating such mappings.

comment: 15 pages, 7 figures

♻ ☆ A Multimodal Data Fusion Generative Adversarial Network for Real Time Underwater Sound Speed Field Construction

Wei Huang, Yuqiang Huang, Yanan Wu, Tianhe Xu, Tingting Lyu, Hao Zhang

Sound speed profiles (SSPs) are essential parameters underwater that affects the propagation mode of underwater signals and has a critical impact on the energy efficiency of underwater acoustic communication and accuracy of underwater acoustic positioning. Traditionally, SSPs can be obtained by matching field processing (MFP), compressive sensing (CS), and deep learning (DL) methods. However, existing methods mainly rely on on-site underwater sonar observation data, which put forward strict requirements on the deployment of sonar observation systems. To achieve high-precision estimation of sound velocity distribution in a given sea area without on-site underwater data measurement, we propose a multi-modal data-fusion generative adversarial network model with residual attention block (MDF-RAGAN) for SSP construction. To improve the model's ability for capturing global spatial feature correlations, we embedded the attention mechanisms, and use residual modules for deeply capturing small disturbances in the deep ocean sound velocity distribution caused by changes of SST. Experimental results on real open dataset show that the proposed model outperforms other state-of-the-art methods, which achieves an accuracy with an error of less than 0.3m/s. Specifically, MDF-RAGAN not only outperforms convolutional neural network (CNN) and spatial interpolation (SITP) by nearly a factor of two, but also achieves about 65.8\% root mean square error (RMSE) reduction compared to mean profile, which fully reflects the enhancement of overall profile matching by multi-source fusion and cross-modal attention.

Audio and Speech Processing 4

☆ HELIX: Scaling Raw Audio Understanding with Hybrid Mamba-Attention Beyond the Quadratic Limit

Khushiyant, Param Thakkar

comment: 10 Pages, 8 Figures

☆ SqueezeComposer: Temporal Speed-up is A Simple Trick for Long-form Music Composing

Jianyi Chen, Rongxiu Zhong, Shilei Zhang, Kun Qian, Jinglei Liu, Yike Guo, Wei Xue

comment: Under Review

☆ Relational graph-driven differential denoising and diffusion attention fusion for multimodal conversation emotion recognition

Ying Liu, Yuntao Shou, Wei Ai, Tao Meng, Keqin Li

comment: 19 pages

♻ ☆ A Multimodal Data Fusion Generative Adversarial Network for Real Time Underwater Sound Speed Field Construction

Wei Huang, Yuqiang Huang, Yanan Wu, Tianhe Xu, Tingting Lyu, Hao Zhang

2026-03-21

Sound 2

☆ The Binding Effect: Analyzing How Multi-Dimensional Cues Form Gender Bias in Instruction TTS INTERSPEECH 2026

Kuan-Yu Chen, Yi-Cheng Lin, Po-Chung Hsieh, Huang-Cheng Chou, Chih-Fan Hsu, Jeng-Lin Li, Hung-yi Lee, Jian-Jiun Ding

Current bias evaluations in Instruction Text-to-Speech (ITTS) often rely on univariate testing, overlooking the compositional structure of social cues. In this work, we investigate gender bias by modeling prompts as combinations of Social Status, Career stereotypes, and Persona descriptors. Analyzing open-source ITTS models, we uncover systematic interaction effects where social dimensions modulate one another, creating complex bias patterns missed by univariate baselines. Crucially, our findings indicate that these biases extend beyond surface-level artifacts, demonstrating strong associations with the semantic priors of pre-trained text encoders and the skewed distributions inherent in training data. We further demonstrate that generic diversity prompting is insufficient to override these entrenched patterns, underscoring the need for compositional analysis to diagnose latent risks in generative speech.

comment: 5 pages, 1 figure, 6 tables, Submitted to INTERSPEECH 2026

☆ SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detection

Kyudan Jung, Jihwan Kim, Minwoo Lee, Soyoon Kim, Jeonghoon Kim, Jaegul Choo, Cheonbok Park

Recent advancements in text-to-speech technologies enable generating high-fidelity synthetic speech nearly indistinguishable from real human voices. While recent studies show the efficacy of self-supervised learning-based speech encoders for deepfake detection, these models struggle to generalize across unseen speakers. Our quantitative analysis suggests these encoder representations are substantially influenced by speaker information, causing detectors to exploit speaker-specific correlations rather than artifact-related cues. We call this phenomenon speaker entanglement. To mitigate this reliance, we introduce SNAP, a speaker-nulling framework. We estimate a speaker subspace and apply orthogonal projection to suppress speaker-dependent components, isolating synthesis artifacts within the residual features. By reducing speaker entanglement, SNAP encourages detectors to focus on artifact-related patterns, leading to state-of-the-art performance.

comment: 9 pages, 3 figures, 2 tables

Audio and Speech Processing 2

☆ OmniCodec: Low Frame Rate Universal Audio Codec with Semantic-Acoustic Disentanglement

Jingbin Hu, Haoyu Zhang, Dake Guo, Qirui Zhan, Wenhao Li, Huakang Chen, Guobin Ma, Hanke Xie, Chengyou Wang, Pengyuan Xie, Chuan Xie, Qiang Zhang, Lei Xie

Large Language Models (LLMs) have advanced audio generation through discrete representation learning. However, most existing neural codecs focus on speech and emphasize reconstruction fidelity, overlooking unified low frame rate modeling across diverse audio domains, including speech, music, and general sound. Moreover, high reconstruction quality does not necessarily yield semantically informative representations, limiting effectiveness in downstream generation tasks. We propose OmniCodec, a universal neural audio codec tailored for low frame rate. It adopts a hierarchical multi-codebook design with semantic-acoustic decoupling by leveraging the audio encoder of the pre-trained understanding model, along with a self-guidance strategy to improve codebook utilization and reconstruction. Compared with the Mimi codec, experiments show that OmniCodec achieves outstanding performance at the same bitrate, delivering superior reconstruction quality while also providing more semantically informative representations that benefit downstream generation tasks. Our model and code will be open-sourced. Our demo page is available.

♻ ☆ Bloodroot: When Watermarking Turns Poisonous For Stealthy Backdoor ICASSP 2026

Kuan-Yu Chen, Yi-Cheng Lin, Jeng-Lin Li, Jian-Jiun Ding

Backdoor data poisoning is a crucial technique for ownership protection and defending against malicious attacks. Embedding hidden triggers in training data can manipulate model outputs, enabling provenance verification, and deterring unauthorized use. However, current audio backdoor methods are suboptimal, as poisoned audio often exhibits degraded perceptual quality, which is noticeable to human listeners. This work explores the intrinsic stealthiness and effectiveness of audio watermarking in achieving successful poisoning. We propose a novel Watermark-as-Trigger concept, integrated into the Bloodroot backdoor framework via adversarial LoRA fine-tuning, which enhances perceptual quality while achieving a much higher trigger success rate and clean-sample accuracy. Experiments on speech recognition (SR) and speaker identification (SID) datasets show that watermark-based poisoning remains effective under acoustic filtering and model pruning. The proposed Bloodroot backdoor framework not only secures data-to-model ownership, but also well reveals the risk of adversarial misuse.

comment: 5 pages, 3 figures accepted to ICASSP 2026

2026-03-20

Sound 15

☆ Audio Avatar Fingerprinting: An Approach for Authorized Use of Voice Cloning in the Era of Synthetic Audio

Candice R. Gerstner

With the advancements in AI speech synthesis, it is easier than ever before to generate realistic audio in a target voice. One only needs a few seconds of reference audio from the target, quite literally putting words in the target person's mouth. This imposes a new set of forensics-related challenges on speech-based authentication systems, videoconferencing, and audio-visual broadcasting platforms, where we want to detect synthetic speech. At the same time, leveraging AI speech synthesis can enhance the different modes of communication through features such as low-bandwidth communication and audio enhancements - leading to ever-increasing legitimate use-cases of synthetic audio. In this case, we want to verify if the synthesized voice is actually spoken by the user. This will require a mechanism to verify whether a given synthetic audio is driven by an authorized identity, or not. We term this task audio avatar fingerprinting. As a step towards audio forensics in these new and emerging situations, we analyze and extend an off-the-shelf speaker verification model developed outside of forensics context for the task of fake speech detection and audio avatar fingerprinting, the first experimentation of its kind. Furthermore, we observe that no existing dataset allows for the novel task of verifying the authorized use of synthetic audio - a limitation which we address by introducing a new speech forensics dataset for this novel task.

☆ BioDCASE 2026 Challenge Baseline for Cross-Domain Mosquito Species Classification DCASE 2026

Yuanbo Hou, Vanja Zdravkovic, Marianne Sinka, Yunpeng Li, Wenwu Wang, Mark D. Plumbley, Kathy Willis, Stephen Roberts

Mosquito-borne diseases affect more than one billion people each year and cause close to one million deaths. Traditional surveillance methods rely on traps and manual identification that are slow, labor-intensive, and difficult to scale. Audio-based mosquito monitoring offers a non-destructive, lower-cost, and more scalable complement to trap-based surveillance, but reliable species classification remains difficult under real-world recording conditions. Mosquito flight tones are narrow-band, often low in signal-to-noise ratio, and easily masked by background noise, and recordings for several epidemiologically relevant species remain limited, creating pronounced class imbalance. Variation across devices, environments, and collection protocols further increases the difficulty of robust classification. Such variation can cause models to rely on domain-specific recording artefacts rather than species-relevant acoustic cues, which makes transfer to new acquisition settings difficult. The BioDCASE 2026 Cross-Domain Mosquito Species Classification (CD-MSC) challenge is designed around this deployment problem by evaluating performance on both seen and unseen domains. This paper presents the official baseline system and evaluation pipeline as a simple, fully reproducible reference for the CD-MSC challenge task. The baseline uses log-mel features and a multitemporal resolution convolutional neural network (MTRCNN) with species and auxiliary domain outputs, together with complete training and test scripts. The baseline system performs strongly on seen domains but degrades markedly on unseen domains, showing that cross-domain generalisation, rather than within-domain recognition, is the central challenge for practical mosquito species classification from multi-source bioacoustic recordings.

comment: BioDCASE 2026 CD-MSC Baseline, source code and models: https://github.com/Yuanbo2020/CD-MSC

☆ FoleyDirector: Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured Scripts CVPR

You Li, Dewei Zhou, Fan Ma, Fu Li, Dongliang He, Yi Yang

Recent Video-to-Audio (V2A) methods have achieved remarkable progress, enabling the synthesis of realistic, high-quality audio. However, they struggle with fine-grained temporal control in multi-event scenarios or when visual cues are insufficient, such as small regions, off-screen sounds, or occluded or partially visible objects. In this paper, we propose FoleyDirector, a framework that, for the first time, enables precise temporal guidance in DiT-based V2A generation while preserving the base model's audio quality and allowing seamless switching between V2A generation and temporally controlled synthesis. FoleyDirector introduces Structured Temporal Scripts (STS), a set of captions corresponding to short temporal segments, to provide richer temporal information. These features are integrated via the Script-Guided Temporal Fusion Module, which employs Temporal Script Attention to fuse STS features coherently. To handle complex multi-event scenarios, we further propose Bi-Frame Sound Synthesis, enabling parallel in-frame and out-of-frame audio generation and improving controllability. To support training and evaluation, we construct the DirectorSound dataset and introduce VGGSoundDirector and DirectorBench. Experiments demonstrate that FoleyDirector substantially enhances temporal controllability while maintaining high audio fidelity, empowering users to act as Foley directors and advancing V2A toward more expressive and controllable generation.

comment: Accepted at IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026, 18 pages

☆ Borderless Long Speech Synthesis

Xingchen Song, Di Wu, Dinghao Zhou, Pengyu Cheng, Hongwu Ding, Yunchao He, Jie Wang, Shengfan Shen, Sixiang Lv, Lichun Fan, Hang Su, Yifeng Wang, Shuai Wang, Meng Meng, Jian Luan

Most existing text-to-speech (TTS) systems either synthesize speech sentence by sentence and stitch the results together, or drive synthesis from plain-text dialogues alone. Both approaches leave models with little understanding of global context or paralinguistic cues, making it hard to capture real-world phenomena such as multi-speaker interactions (interruptions, overlapping speech), evolving emotional arcs, and varied acoustic environments. We introduce the Borderless Long Speech Synthesis framework for agent-centric, borderless long audio synthesis. Rather than targeting a single narrow task, the system is designed as a unified capability set spanning VoiceDesigner, multi-speaker synthesis, Instruct TTS, and long-form text synthesis. On the data side, we propose a "Labeling over filtering/cleaning" strategy and design a top-down, multi-level annotation schema we call Global-Sentence-Token. On the model side, we adopt a backbone with a continuous tokenizer and add Chain-of-Thought (CoT) reasoning together with Dimension Dropout, both of which markedly improve instruction following under complex conditions. We further show that the system is Native Agentic by design: the hierarchical annotation doubles as a Structured Semantic Interface between the LLM Agent and the synthesis engine, creating a layered control protocol stack that spans from scene semantics down to phonetic detail. Text thereby becomes an information-complete, wide-band control channel, enabling a front-end LLM to convert inputs of any modality into structured generation commands, extending the paradigm from Text2Speech to borderless long speech synthesis.

☆ MOSS-TTSD: Text to Spoken Dialogue Generation

Yuqian Zhang, Donghua Yu, Zhengyuan Lin, Botian Jiang, Mingshu Chen, Yaozhou Jiang, Yiwei Zhao, Yiyang Zhang, Yucheng Yuan, Hanfu Chen, Kexin Huang, Jun Zhan, Cheng Chang, Zhaoye Fei, Shimin Li, Xiaogui Yang, Qinyuan Cheng, Xipeng Qiu

Spoken dialogue generation is crucial for applications like podcasts, dynamic commentary, and entertainment content, but poses significant challenges compared to single-utterance text-to-speech (TTS). Key requirements include accurate turn-taking, cross-turn acoustic consistency, and long-form stability, which current models often fail to address due to a lack of dialogue context modeling. To bridge this gap, we present MOSS-TTSD, a spoken dialogue synthesis model designed for expressive, multi-party conversational speech across multiple languages. With enhanced long-context modeling, MOSS-TTSD generates long-form spoken conversations from dialogue scripts with explicit speaker tags, supporting up to 60 minutes of single-pass synthesis, multi-party dialogue with up to 5 speakers, and zero-shot voice cloning from a short reference audio clip. The model supports various mainstream languages, including English and Chinese, and is adapted to several long-form scenarios. Additionally, to address limitations of existing evaluation methods, we propose TTSD-eval, an objective evaluation framework based on forced alignment that measures speaker attribution accuracy and speaker similarity without relying on speaker diarization tools. Both objective and subjective evaluation results show that MOSS-TTSD surpasses strong open-source and proprietary baselines in dialogue synthesis.

☆ Plug-and-Steer: Decoupling Separation and Selection in Audio-Visual Target Speaker Extraction

Doyeop Kwak, Suyeon Lee, Joon Son Chung

The goal of this paper is to provide a new perspective on audio-visual target speaker extraction (AV-TSE) by decoupling the separation and target selection. Conventional AV-TSE systems typically integrate audio and visual features deeply to re-learn the entire separation process, which can act as a fidelity ceiling due to the noisy nature of in-the-wild audio-visual datasets. To address this, we propose Plug-and-Steer, which assigns high-fidelity separation to a frozen audio-only backbone and limits the role of visual modality strictly to target selection. We introduce the Latent Steering Matrix (LSM), a minimalist linear transformation that re-routes latent features within the backbone to anchor the target speaker to a designated channel. Experiments across four representative architectures show that our method effectively preserves the acoustic priors of diverse backbones, achieving perceptual quality comparable to the original backbones. Audio samples are available at: https://plugandsteer.github.io

comment: Submitted to Interspeech 2026; demo available https://plugandsteer.github.io

☆ CAF-Score: Calibrating CLAP with LALMs for Reference-free Audio Captioning Evaluation

Insung Lee, Taeyoung Jeong, Haejun Yoo, Du-Seong Chang, Myoung-Wan Koo

While Large Audio-Language Models (LALMs) have advanced audio captioning, robust evaluation remains difficult. Reference-based metrics are expensive and often fail to assess acoustic fidelity, while Contrastive Language-Audio Pretraining (CLAP)-based approaches frequently overlook syntactic errors and fine-grained details. We propose CAF-Score, a reference-free metric that calibrates CLAP's coarse-grained semantic alignment with the fine-grained comprehension and syntactic awareness of LALMs. By combining contrastive audio-text embeddings with LALM reasoning, CAF-Score effectively detects syntactic inconsistencies and subtle hallucinations. Experiments on the BRACE benchmark demonstrate that our approach achieves the highest correlation with human judgments, even outperforming reference-based baselines in challenging scenarios. These results highlight the efficacy of CAF-Score for reference-free audio captioning evaluation. Code and results are available at https://github.com/inseong00/CAF-Score.

comment: A condensed version of this work has been submitted to Interspeech 2026. Section 10 is an extended analysis added in this version

☆ ALICE: A Multifaceted Evaluation Framework of Large Audio-Language Models' In-Context Learning Ability

Yen-Ting Piao, Jay Chiehen Liao, Wei-Tang Chien, Toshiki Ogimoto, Shang-Tse Chen, Yun-Nung Chen, Chun-Yi Lee, Shao-Yuan Lo

While Large Audio-Language Models (LALMs) have been shown to exhibit degraded instruction-following capabilities, their ability to infer task patterns from in-context examples under audio conditioning remains unstudied. To address this gap, we present ALICE, a three-stage framework that progressively reduces textual guidance to systematically evaluate LALMs' in-context learning ability under audio conditioning. Evaluating six LALMs across four audio understanding tasks under two output constraint categories, we uncover a consistent asymmetry across all stages and LALMs: in-context demonstrations reliably improve format compliance but fail to improve, and often degrade, the core task performance. This suggests that LALMs can glean surface-level formatting patterns from demonstrations but may struggle to leverage cross-modal semantic grounding to reliably infer task objectives from audio-conditioned examples, highlighting potential limitations in current cross-modal integration.

comment: Submitted to Interspeech 2026

☆ End-to-End Multi-Task Learning for Adjustable Joint Noise Reduction and Hearing Loss Compensation

Philippe Gonzalez, Vera Margrethe Frederiksen, Torsten Dau, Tobias May

A multi-task learning framework is proposed for optimizing a single deep neural network (DNN) for joint noise reduction (NR) and hearing loss compensation (HLC). A distinct training objective is defined for each task, and the DNN predicts two time-frequency masks. During inference, the amounts of NR and HLC can be adjusted independently by exponentiating each mask before combining them. In contrast to recent approaches that rely on training an auditory-model emulator to define a differentiable training objective, we propose an auditory model that is inherently differentiable, thus allowing end-to-end optimization. The audiogram is provided as an input to the DNN, thereby enabling listener-specific personalization without the need for retraining. Results show that the proposed approach not only allows adjusting the amounts of NR and HLC individually, but also improves objective metrics compared to optimizing a single training objective. It also outperforms a cascade of two DNNs that were separately trained for NR and HLC, and shows competitive HLC performance compared to a traditional hearing-aid prescription. To the best of our knowledge, this is the first study that uses an auditory model to train a single DNN for both NR and HLC across a wide range of listener profiles.

☆ ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography

Jing Xu, Weiqiang Wang, Cunjian Chen, Jun Liu, Qiuhong Ke

Group dance generation from music requires synchronizing multiple dancers while maintaining spatial coordination, making it highly relevant to applications such as film production, gaming, and animation. Recent group dance generation models have achieved promising generation quality, but they remain difficult to deploy in interactive scenarios due to bidirectional attention dependencies. As the number of dancers and the sequence length increase, the attention computation required for aligning music conditions with motion sequences grows quadratically, leading to reduced efficiency and increased risk of motion collisions. Effectively modeling dense spatial-temporal interactions is therefore essential, yet existing methods often struggle to capture such complexity, resulting in limited scalability and unstable multi-dancer coordination. To address these challenges, we propose ST-GDance++, a scalable framework that decouples spatial and temporal dependencies to enable efficient and collision-aware group choreography generation. For spatial modeling, we introduce lightweight distance-aware graph convolutions to capture inter-dancer relationships while reducing computational overhead. For temporal modeling, we design a diffusion noise scheduling strategy together with an efficient temporal-aligned attention mask, enabling stream-based generation for long motion sequences and improving scalability in long-duration scenarios. Experiments on the AIOZ-GDance dataset show that ST-GDance++ achieves competitive generation quality with significantly reduced latency compared to existing methods.

☆ Semantic Audio-Visual Navigation in Continuous Environments CVPR 2026

Yichen Zeng, Hebaixu Wang, Meng Liu, Yu Zhou, Chen Gao, Kehan Chen, Gongping Huang

Audio-visual navigation enables embodied agents to navigate toward sound-emitting targets by leveraging both auditory and visual cues. However, most existing approaches rely on precomputed room impulse responses (RIRs) for binaural audio rendering, restricting agents to discrete grid positions and leading to spatially discontinuous observations. To establish a more realistic setting, we introduce Semantic Audio-Visual Navigation in Continuous Environments (SAVN-CE), where agents can move freely in 3D spaces and perceive temporally and spatially coherent audio-visual streams. In this setting, targets may intermittently become silent or stop emitting sound entirely, causing agents to lose goal information. To tackle this challenge, we propose MAGNet, a multimodal transformer-based model that jointly encodes spatial and semantic goal representations and integrates historical context with self-motion cues to enable memory-augmented goal reasoning. Comprehensive experiments demonstrate that MAGNet significantly outperforms state-of-the-art methods, achieving up to a 12.1\% absolute improvement in success rate. These results also highlight its robustness to short-duration sounds and long-distance navigation scenarios. The code is available at https://github.com/yichenzeng24/SAVN-CE.

comment: This paper has been accepted to CVPR 2026

♻ ☆ AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer ICLR 2026

Pengjun Fang, Yingqing He, Yazhou Xing, Qifeng Chen, Ser-Nam Lim, Harry Yang

Existing video-to-audio (V2A) generation methods predominantly rely on text prompts alongside visual information to synthesize audio. However, two critical bottlenecks persist: semantic granularity gaps in training data, such as conflating acoustically distinct sounds under coarse labels, and textual ambiguity in describing micro-acoustic features. These bottlenecks make it difficult to perform fine-grained sound synthesis using text-controlled modes. To address these limitations, we propose AC-Foley, an audio-conditioned V2A model that directly leverages reference audio to achieve precise and fine-grained control over generated sounds. This approach enables fine-grained sound synthesis, timbre transfer, zero-shot sound generation, and improved audio quality. By directly conditioning on audio signals, our approach bypasses the semantic ambiguities of text descriptions while enabling precise manipulation of acoustic attributes. Empirically, AC-Foley achieves state-of-the-art performance for Foley generation when conditioned on reference audio, while remaining competitive with state-of-the-art video-to-audio methods even without audio conditioning. Code and demo are available at: https://ff2416.github.io/AC-Foley-Page

comment: Accepted at ICLR 2026. 15 pages, 5 figures, add project webpage

♻ ☆ MOSS-TTS Technical Report

Yitian Gong, Botian Jiang, Yiwei Zhao, Yucheng Yuan, Kuangwei Chen, Yaozhou Jiang, Cheng Chang, Dong Hong, Mingshu Chen, Ruixiao Li, Yiyang Zhang, Yang Gao, Hanfu Chen, Ke Chen, Songlin Wang, Xiaogui Yang, Yuqian Zhang, Kexin Huang, ZhengYuan Lin, Kang Yu, Ziqi Chen, Jin Wang, Zhaoye Fei, Qinyuan Cheng, Shimin Li, Xipeng Qiu

This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer tokenizer that compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations, we release two complementary generators: MOSS-TTS, which emphasizes structural simplicity, scalability, and long-context/control-oriented deployment, and MOSS-TTS-Local-Transformer, which introduces a frame-local autoregressive module for higher modeling efficiency, stronger speaker preservation, and a shorter time to first audio. Across multilingual and open-domain settings, MOSS-TTS supports zero-shot voice cloning, token-level duration control, phoneme-/pinyin-level pronunciation control, smooth code-switching, and stable long-form generation. This report summarizes the design, training recipe, and empirical characteristics of the released models.

comment: Project page: https://github.com/OpenMOSS/MOSS-TTS

♻ ☆ VSSFlow: Unifying Video-conditioned Sound and Speech Generation via Joint Learning

Xin Cheng, Yuyue Wang, Xihua Wang, Yihan Wu, Kaisi Guan, Yijing Chen, Peng Zhang, Xiaojiang Liu, Meng Cao, Ruihua Song

Video-conditioned audio generation, including Video-to-Sound (V2S) and Visual Text-to-Speech (VisualTTS), has traditionally been treated as distinct tasks, leaving the potential for a unified generative framework largely underexplored. In this paper, we bridge this gap with VSSFlow, a unified flow-matching framework that seamlessly solve both problems. To effectively handle multiple input signals within a Diffusion Transformer (DiT) architecture, we propose a disentangled condition aggregation mechanism leveraging distinct intrinsic properties of attention layers: cross-attention for semantic conditions, and self-attention for temporally-intensive conditions. Besides, contrary to the prevailing belief that joint training for the two tasks leads to performance degradation, we demonstrate that VSSFlow maintains superior performance during end-to-end joint learning process. Furthermore, we use a straightforward feature-level data synthesis method, demonstrating that our framework provides a robust foundation that easily adapts to joint sound and speech generation using synthetic data. Extensive experiments on V2S, VisualTTS and joint generation benchmarks show that VSSFlow effectively unifies these tasks and surpasses state-of-the-art domain-specific baselines, underscoring the critical potential of unified generative models. Project page: https://vasflow1.github.io/vasflow/

comment: Paper Under Review

♻ ☆ DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language Models

Jiaqi Xiong, Yunjia Qi, Qi Cao, Yu Zheng, Yutong Zhang, Ziteng Wang, Ruofan Liao, Weisheng Xu, Sichen Liu

Recent Audio Multimodal Large Language Models (Audio MLLMs) demonstrate impressive performance on speech benchmarks, yet it remains unclear whether these models genuinely process acoustic signals or rely on text-based semantic inference. To systematically study this question, we introduce DEAF (Diagnostic Evaluation of Acoustic Faithfulness), a benchmark of over 2,700 conflict stimuli spanning three acoustic dimensions: emotional prosody, background sounds, and speaker identity. Then, we design a controlled multi-level evaluation framework that progressively increases textual influence, ranging from semantic conflicts in the content to misleading prompts and their combination, allowing us to disentangle content-driven bias from prompt-induced sycophancy. We further introduce diagnostic metrics to quantify model reliance on textual cues over acoustic signals. Our evaluation of seven Audio MLLMs reveals a consistent pattern of text dominance: models are sensitive to acoustic variations, yet predictions are predominantly driven by textual inputs, revealing a gap between high performance on standard speech benchmarks and genuine acoustic understanding.

comment: 14 pages,6 figures

Audio and Speech Processing 11

☆ Audio Avatar Fingerprinting: An Approach for Authorized Use of Voice Cloning in the Era of Synthetic Audio

Candice R. Gerstner

☆ BioDCASE 2026 Challenge Baseline for Cross-Domain Mosquito Species Classification DCASE 2026

Yuanbo Hou, Vanja Zdravkovic, Marianne Sinka, Yunpeng Li, Wenwu Wang, Mark D. Plumbley, Kathy Willis, Stephen Roberts

comment: BioDCASE 2026 CD-MSC Baseline, source code and models: https://github.com/Yuanbo2020/CD-MSC

☆ Gesture2Speech: How Far Can Hand Movements Shape Expressive Speech? AAAI 2026

Lokesh Kumar, Nirmesh Shah, Ashishkumar P. Gudmalwar, Pankaj Wasnik

Human communication seamlessly integrates speech and bodily motion, where hand gestures naturally complement vocal prosody to express intent, emotion, and emphasis. While recent text-to-speech (TTS) systems have begun incorporating multimodal cues such as facial expressions or lip movements, the role of hand gestures in shaping prosody remains largely underexplored. We propose a novel multimodal TTS framework, Gesture2Speech, that leverages visual gesture cues to modulate prosody in synthesized speech. Motivated by the observation that confident and expressive speakers coordinate gestures with vocal prosody, we introduce a multimodal Mixture-of-Experts (MoE) architecture that dynamically fuses linguistic content and gesture features within a dedicated style extraction module. The fused representation conditions an LLM-based speech decoder, enabling prosodic modulation that is temporally aligned with hand movements. We further design a gesture-speech alignment loss that explicitly models their temporal correspondence to ensure fine-grained synchrony between gestures and prosodic contours. Evaluations on the PATS dataset show that Gesture2Speech outperforms state-of-the-art baselines in both speech naturalness and gesture-speech synchrony. To the best of our knowledge, this is the first work to utilize hand gesture cues for prosody control in neural speech synthesis. Demo samples are available at https://research.sri-media-analysis.com/aaai26-beeu-gesture2speech/

comment: Accepted at The 2nd International Workshop on Bodily Expressed Emotion Understanding (BEEU) at AAAI 2026 [non-archival]

☆ Borderless Long Speech Synthesis

Xingchen Song, Di Wu, Dinghao Zhou, Pengyu Cheng, Hongwu Ding, Yunchao He, Jie Wang, Shengfan Shen, Sixiang Lv, Lichun Fan, Hang Su, Yifeng Wang, Shuai Wang, Meng Meng, Jian Luan

☆ Plug-and-Steer: Decoupling Separation and Selection in Audio-Visual Target Speaker Extraction

Doyeop Kwak, Suyeon Lee, Joon Son Chung

comment: Submitted to Interspeech 2026; demo available https://plugandsteer.github.io

☆ ALICE: A Multifaceted Evaluation Framework of Large Audio-Language Models' In-Context Learning Ability

Yen-Ting Piao, Jay Chiehen Liao, Wei-Tang Chien, Toshiki Ogimoto, Shang-Tse Chen, Yun-Nung Chen, Chun-Yi Lee, Shao-Yuan Lo

comment: Submitted to Interspeech 2026

☆ End-to-End Multi-Task Learning for Adjustable Joint Noise Reduction and Hearing Loss Compensation

Philippe Gonzalez, Vera Margrethe Frederiksen, Torsten Dau, Tobias May

♻ ☆ Community-Informed AI Models for Police Accountability

Benjamin A. T. Grahama, Lauren Brown, Georgios Chochlakis, Morteza Dehghani, Raquel Delerme, Brittany Friedman, Ellie Graeden, Preni Golazizian, Rajat Hebbar, Parsa Hejabi, Aditya Kommineni, Mayagüez Salinas, Michael Sierra-Arévalo, Jackson Trager, Nicholas Weller, Shrikanth Narayanan

Face-to-face interactions between police officers and the public affect both individual well-being and democratic legitimacy. Many government-public interactions are captured on video, including interactions between police officers and drivers captured on bodyworn cameras (BWCs). New advances in AI technology enable these interactions to be analyzed at scale, opening promising avenues for improving government transparency and accountability. However, for AI to serve democratic governance effectively, models must be designed to include the preferences and perspectives of the governed. This article proposes a community-informed, approach to developing multi-perspective AI tools for government accountability. We illustrate our approach by describing the research project through which the approach was inductively developed: an effort to build AI tools to analyze BWC footage of traffic stops conducted by the Los Angeles Police Department. We focus on the role of social scientists as members of multidisciplinary teams responsible for integrating the perspectives of diverse stakeholders into the development of AI tools in the domain of police -- and government -- accountability.

comment: 33 pages, 4 figures, 2 tables

♻ ☆ AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer ICLR 2026

Pengjun Fang, Yingqing He, Yazhou Xing, Qifeng Chen, Ser-Nam Lim, Harry Yang

comment: Accepted at ICLR 2026. 15 pages, 5 figures, add project webpage

♻ ☆ VSSFlow: Unifying Video-conditioned Sound and Speech Generation via Joint Learning

Xin Cheng, Yuyue Wang, Xihua Wang, Yihan Wu, Kaisi Guan, Yijing Chen, Peng Zhang, Xiaojiang Liu, Meng Cao, Ruihua Song

comment: Paper Under Review

♻ ☆ DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language Models

Jiaqi Xiong, Yunjia Qi, Qi Cao, Yu Zheng, Yutong Zhang, Ziteng Wang, Ruofan Liao, Weisheng Xu, Sichen Liu

comment: 14 pages,6 figures

2026-03-19

Sound 15

☆ How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation

Ke-Han Lu, Szu-Wei Fu, Chao-Han Huck Yang, Zhehuai Chen, Sung-Feng Huang, Chih-Kai Yang, Yi-Cheng Lin, Chi-Yuan Hsiao, Wenze Ren, En-Pei Hu, Yu-Han Huang, An-Yu Cheng, Cheng-Han Chiang, Yu Tsao, Yu-Chiang Frank Wang, Hung-yi Lee

Large language models (LLMs) have been widely used as knowledge backbones of Large Audio Language Models (LALMs), yet how much auditory knowledge they encode through text-only pre-training and how this affects downstream performance remains unclear. We study this gap by comparing different LLMs under two text-only and one audio-grounded setting: (1) direct probing on AKB-2000, a curated benchmark testing the breadth and depth of auditory knowledge; (2) cascade evaluation, where LLMs reason over text descriptions from an audio captioner; and (3) audio-grounded evaluation, where each LLM is fine-tuned into a Large Audio Language Model (LALM) with an audio encoder. Our findings reveal that auditory knowledge varies substantially across families, and text-only results are strongly correlated with audio performance. Our work provides empirical grounding for a comprehensive understanding of LLMs in audio research.

comment: Project website: https://kehanlu.github.io/AKB

☆ Few-shot Acoustic Synthesis with Multimodal Flow Matching CVPR 2026

Amandine Brunetto

Generating audio that is acoustically consistent with a scene is essential for immersive virtual environments. Recent neural acoustic field methods enable spatially continuous sound rendering but remain scene-specific, requiring dense audio measurements and costly training for each environment. Few-shot approaches improve scalability across rooms but still rely on multiple recordings and, being deterministic, fail to capture the inherent uncertainty of scene acoustics under sparse context. We introduce flow-matching acoustic generation (FLAC), a probabilistic method for few-shot acoustic synthesis that models the distribution of plausible room impulse responses (RIRs) given minimal scene context. FLAC leverages a diffusion transformer trained with a flow-matching objective to generate RIRs at arbitrary positions in novel scenes, conditioned on spatial, geometric, and acoustic cues. FLAC outperforms state-of-the-art eight-shot baselines with one-shot on both the AcousticRooms and Hearing Anything Anywhere datasets. To complement standard perceptual metrics, we further introduce AGREE, a joint acoustic-geometry embedding, enabling geometry-consistent evaluation of generated RIRs through retrieval and distributional metrics. This work is the first to apply generative flow matching to explicit RIR synthesis, establishing a new direction for robust and data-efficient acoustic synthesis.

comment: To appear at CVPR 2026. 23 pages, 16 figures. Project Page: https://amandinebtto.github.io/FLAC/

☆ Dual-Model Prediction of Affective Engagement and Vocal Attractiveness from Speaker Expressiveness in Video Learning

Hung-Yue Suen, Kuo-En Hung, Fan-Hsun Tseng

This paper outlines a machine learning-enabled speaker-centric Emotion AI approach capable of predicting audience-affective engagement and vocal attractiveness in asynchronous video-based learning, relying solely on speaker-side affective expressions. Inspired by the demand for scalable, privacy-preserving affective computing applications, this speaker-centric Emotion AI approach incorporates two distinct regression models that leverage a massive corpus developed within Massive Open Online Courses (MOOCs) to enable affectively engaging experiences. The regression model predicting affective engagement is developed by assimilating emotional expressions emanating from facial dynamics, oculomotor features, prosody, and cognitive semantics, while incorporating a second regression model to predict vocal attractiveness based exclusively on speaker-side acoustic features. Notably, on speaker-independent test sets, both regression models yielded impressive predictive performance (R2 = 0.85 for affective engagement and R2 = 0.88 for vocal attractiveness), confirming that speaker-side affect can functionally represent aggregated audience feedback. This paper provides a speaker-centric Emotion AI approach substantiated by an empirical study discovering that speaker-side multimodal features, including acoustics, can prospectively forecast audience feedback without necessarily employing audience-side input information.

comment: Preprint. Accepted for publication in IEEE Transactions on Computational Social Systems

☆ Words at Play: Benchmarking Audio Pun Understanding in Large Audio-Language Models

Yuchen Su, Shaoxin Zhong, Yonghua Zhu, Ruofan Wang, Zijian Huang, Qiqi Wang, Na Zhao, Diana Benavides-Prado, Michael Witbrock

Puns represent a typical linguistic phenomenon that exploits polysemy and phonetic ambiguity to generate humour, posing unique challenges for natural language understanding. Within pun research, audio plays a central role in human communication except text and images, while datasets and systematic resources for spoken puns remain scarce, leaving this crucial modality largely underexplored. In this paper, we present APUN-Bench, the first benchmark dedicated to evaluating large audio language models (LALMs) on audio pun understanding. Our benchmark contains 4,434 audio samples annotated across three stages: pun recognition, pun word location and pun meaning inference. We conduct a deep analysis of APUN-Bench by systematically evaluating 10 state-of-the-art LALMs, uncovering substantial performance gaps in recognizing, localizing, and interpreting audio puns. This analysis reveals key challenges, such as positional biases in audio pun location and error cases in meaning inference, offering actionable insights for advancing humour-aware audio intelligence.

comment: The paper is currently under review

☆ DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units

Maxime Poli, Manel Khentout, Angelo Ortiz Tandazo, Ewan Dunbar, Emmanuel Chemla, Emmanuel Dupoux

We introduce DiscoPhon, a multilingual benchmark for evaluating unsupervised phoneme discovery from discrete speech units. DiscoPhon covers 6 dev and 6 test languages, chosen to span a wide range of phonemic contrasts. Given only 10 hours of speech in a previously unseen language, systems must produce discrete units that are mapped to a predefined phoneme inventory, through either a many-to-one or a one-to-one assignment. The resulting sequences are evaluated for unit quality, recognition and segmentation. We provide four pretrained multilingual HuBERT and SpidR baselines, and show that phonemic information is available enough in current models for derived units to correlate well with phonemes, though with variations across languages.

comment: 6 pages, 2 figures. Submitted to Interspeech 2026

☆ Listen First, Then Answer: Timestamp-Grounded Speech Reasoning

Jihoon Jeong, Pooneh Mousavi, Mirco Ravanelli, Cem Subakan

Large audio-language models (LALMs) can generate reasoning chains for their predictions, but it remains unclear whether these reasoning chains remain grounded in the input audio. In this paper, we propose an RL-based strategy that grounds the reasoning outputs of LALMs with explicit timestamp annotations referring to relevant segments of the audio signal. Our analysis shows that timestamp grounding leads the model to attend more strongly to audio tokens during reasoning generation. Experiments on four speech-based benchmark datasets demonstrate that our approach improves performance compared to both zero-shot reasoning and fine-tuning without timestamp grounding. Additionally, grounding amplifies desirable reasoning behaviors, such as region exploration, audiology verification, and consistency, underscoring the importance of grounding mechanisms for faithful multimodal reasoning.

comment: Submitted to Interspeech 2026

☆ EARTalking: End-to-end GPT-style Autoregressive Talking Head Synthesis with Frame-wise Control

Yuzhe Weng, Haotian Wang, Yuanhong Yu, Jun Du, Shan He, Xiaoyan Wu, Haoran Xu

Audio-driven talking head generation aims to create vivid and realistic videos from a static portrait and speech. Existing AR-based methods rely on intermediate facial representations, which limit their expressiveness and realism. Meanwhile, diffusion-based methods generate clip-by-clip, lacking fine-grained control and causing inherent latency due to overall denoising across the window. To address these limitations, we propose EARTalking, a novel end-to-end, GPT-style autoregressive model for interactive audio-driven talking head generation. Our method introduces a novel frame-by-frame, in-context, audio-driven streaming generation paradigm. For inherently supporting variable-length video generation with identity consistency, we propose the Sink Frame Window Attention (SFA) mechanism. Furthermore, to avoid the complex, separate networks that prior works required for diverse control signals, we propose a streaming Frame Condition In-Context (FCIC) scheme. This scheme efficiently injects diverse control signals in a streaming, in-context manner, enabling interactive control at every frame and at arbitrary moments. Experiments demonstrate that EARTalking outperforms existing autoregressive methods and achieves performance comparable to diffusion-based methods. Our work demonstrates the feasibility of in-context streaming autoregressive control, unlocking a scalable direction for flexible, efficient generation. The code will be released for reproducibility.

☆ Voice Privacy from an Attribute-based Perspective

Mehtab Ur Rahman, Martha Larson, Cristian Tejedor García

comment: Submitted to InterSpeech 2026

♻ ☆ DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment

Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, Chao-Han Huck Yang, Sung-Feng Huang, Chih-Kai Yang, Chee-En Yu, Chun-Wei Chen, Wei-Chih Chen, Chien-yu Huang, Yi-Cheng Lin, Yu-Xiang Lin, Chi-An Fu, Chun-Yi Kuan, Wenze Ren, Xuanjun Chen, Wei-Ping Huang, En-Pei Hu, Tzu-Quan Lin, Yuan-Kuei Wu, Kuan-Po Huang, Hsiao-Ying Huang, Huang-Cheng Chou, Kai-Wei Chang, Cheng-Han Chiang, Boris Ginsburg, Yu-Chiang Frank Wang, Hung-yi Lee

We introduce DeSTA2.5-Audio, a general-purpose Large Audio Language Model (LALM) designed for robust auditory perception and instruction-following. Recent LALMs augment Large Language Models (LLMs) with auditory capabilities by training on large-scale audio-instruction datasets. However, existing LALMs have often suffered from the catastrophic forgetting of the LLM's original abilities. Therefore, balancing knowledge retention and audio perception has become a critical challenge. To address this, we revisit the data construction pipeline and propose a self-generated cross-modal alignment strategy in which the backbone LLM generates its own training targets, named DeSTA. This approach aims at preserving the LLM's native language proficiency thereby enabling zero-shot generalization without task-specific tuning. We construct DeSTA-AQA5M, a large-scale, task-agnostic dataset containing 5 million training samples derived from 7,000 hours of audio spanning 50 diverse datasets, including speech, environmental sounds, and music. DeSTA2.5-Audio achieves state-of-the-art or competitive performance across a wide range of audio-language benchmarks, including Dynamic-SUPERB, MMAU, SAKURA, Speech-IFEval, and VoiceBench. Comprehensive comparative studies demonstrate that our self-generated strategy outperforms existing training strategies. Our findings underscore the importance of carefully designed data construction in LALM development and offer practical insights for building robust, general-purpose LALMs.

comment: Published in IEEE Transactions on Audio, Speech and Language Processing (TASLP). Model and code available at: https://github.com/kehanlu/DeSTA2.5-Audio

♻ ☆ Affect Decoding in Phonated and Silent Speech Production from Surface EMG

Simon Pistrosch, Kleanthis Avramidis, Zhao Ren, Tiantian Feng, Jihwan Lee, Monica Gonzalez-Machorro, Anton Batliner, Tanja Schultz, Shrikanth Narayanan, Björn W. Schuller

The expression of affect is integral to spoken communication, yet, its link to underlying articulatory execution remains unclear. Measures of articulatory muscle activity such as EMG could reveal how speech production is modulated by emotion alongside acoustic speech analyses. We investigate affect decoding from facial and neck surface electromyography (sEMG) during phonated and silent speech production. For this purpose, we introduce a dataset comprising 2,780 utterances from 12 participants across 3 tasks, on which we evaluate both intra- and inter-subject decoding using a range of features and model embeddings. Our results reveal that EMG representations reliably discriminate frustration with up to 0.845 AUC, and generalize well across articulation modes. Our ablation study further demonstrates that affective signatures are embedded in facial motor activity and persist in the absence of phonation, highlighting the potential of EMG sensing for affect-aware silent speech interfaces.

♻ ☆ Fair-Gate: Fairness-Aware Interpretable Risk Gating for Sex-Fair Voice Biometrics

Yangyang Qu, Todisco Massimiliano, Galdi Chiara, Evans Nicholas

♻ ☆ Zipper-LoRA: Dynamic Parameter Decoupling for Speech-LLM based Multilingual Speech Recognition

Yuxiang Mei, Delai Qiu, Shengping Liu, Jiaen Liang, Yanhua Long

Speech Large Language Models (Speech-LLMs) have emerged as a powerful approach for automatic speech recognition (ASR) by aligning speech encoders with large language models. However, adapting these systems to multilingual settings with imbalanced data distributions remains challenging. In such scenarios, a stability-plasticity dilemma often arises: fully shared Parameter-Efficient Fine-Tuning (PEFT) can cause negative inter-lingual interference for under-represented languages, while fully language-specific tuning limits the cross-lingual beneficial knowledge transfer needed for low-resource tasks. To address this, we propose Zipper-LoRA, a novel rank-level decoupling framework with three variants (Static, Hard, and Soft) that dynamically synthesizes LoRA updates from shared and language-specific subspaces. By using a lightweight language-conditioned router, Zipper-LoRA dynamically controls the contribution of each subspace at the LoRA rank level, enabling fine-grained sharing where languages are compatible and strict decoupling when conflicts occur. To further stabilize optimization under imbalanced data, we propose a two-stage training strategy with an Initial-B warm start that significantly accelerates convergence. Experiments on a 12-language mixed-resource setting show that Zipper-LoRA consistently outperforms both fully shared and independent baselines, particularly in extremely low-resource scenarios. Moreover, we demonstrate that these gains are robust across both chunked and non-chunked encoder configurations, confirming the framework's reliability for practical, large-scale multilingual ASR. Our code and data will be available at https://github.com/YuCeong-May/Zipper-LoRA for reproducibility.

comment: 13 pages, 8 figures

♻ ☆ MPDR Beamforming for Almost-Cyclostationary Processes

Giovanni Bologni, Martin Bo Møller, Richard Heusdens, Richard C. Hendriks

Conventional acoustic beamformers typically assume short-time stationarity and process frequency bins independently, ignoring inter-frequency correlations. This is suboptimal for almost-periodic noise sources such as engines, fans, and musical instruments: these signals are better modeled as (almost) cyclostationary (ACS) processes with statistically correlated spectral components. This paper introduces the cyclic minimum power distortionless response (cMPDR) beamformer, which extends the conventional MPDR to jointly exploit spatial and spectral correlations. Building on frequency-shifted (FRESH) filtering, it suppresses noise components that are coherent across harmonically related frequencies, reducing residual noise beyond what spatial filtering alone achieves. To address inharmonicity, where partials deviate from exact integer multiples of a fundamental frequency, we estimate resonant frequencies from a periodogram and derive frequency shifts from their pairwise spacing. Theoretical analysis yields closed-form expressions for residual noise and proves that output power decreases monotonically with the number of cyclic components. Experiments on synthetic harmonic noise and real UAV motor recordings confirm these findings: in low-SNR scenarios, the cMPDR achieves up to 5dB improvement in SI-SDR over the MPDR, yields consistent STOI gains, and remains effective with a single microphone. When spectral correlation is absent, the method reduces to conventional MPDR and does not degrade performance. These results suggest that cyclic processing is a viable direction for acoustic noise reduction that deserves further investigation. Code is available at https://github.com/Screeen/cMPDR.

comment: This work has been submitted to the IEEE for possible publication

♻ ☆ Evaluating Hallucinations in Audio-Visual Multimodal LLMs with Spoken Queries under Diverse Acoustic Conditions

Hansol Park, Hoseong Ahn, Junwon Moon, Yejin Lee, Kyuhong Shim

Hallucinations in multimodal models have been extensively studied using benchmarks that probe reliability in image-text query settings. However, the effect of spoken queries on multimodal hallucinations remains largely unexplored, despite the growing role of voice interfaces. In this paper, we introduce a systematic pipeline that converts existing multimodal hallucination benchmarks into spoken-query versions while preserving the original tasks and labels. We instantiate this pipeline on RePOPE and release RePOPE-Spk, where all queries are provided as spoken audio under diverse input conditions. Experimental results show that hallucinations escalate when queries are spoken rather than written: error rates increase by 3-6% with clean speech and by up to 30% under environmental noise. Furthermore, many-shot prompting and chain-of-thought reasoning provide only partial mitigation. Our findings motivate new directions for building reliable voice interface systems and evaluations.

comment: Submitted to Interspeech2026

♻ ☆ GLAD: Global-Local Aware Dynamic Mixture-of-Experts for Multi-Talker ASR

Yujie Guo, Jiaming Zhou, Yuhang Jia, Shiwan Zhao, Yong Qin

End-to-end multi-talker automatic speech recognition (MTASR) faces significant challenges in accurately transcribing overlapping speech. A critical bottleneck is that speaker-specific acoustic characteristics, which are essential for distinguishing overlapping speech, are often diluted in deep network layers. To address this, we propose the Global-Local Aware Dynamic Mixture-of-Experts (GLAD) architecture. GLAD introduces a novel routing mechanism that dynamically fuses speaker-aware global context with fine-grained local acoustic details to adaptively guide expert selection. Experiments on the LibriSpeechMix and CH109 datasets demonstrate that GLAD significantly outperforms existing Serialized Output Training (SOT)-based MTASR approaches, exhibiting exceptional robustness in challenging, high-overlap scenarios. To the best of our knowledge, this is the first work to apply a global-local fusion MoE strategy to MTASR.

comment: This paper has been submitted to Interspeech 2026 for review

Audio and Speech Processing 12

☆ How Auditory Knowledge in LLM Backbones Shapes Audio Language Models: A Holistic Evaluation

comment: Project website: https://kehanlu.github.io/AKB

☆ Few-shot Acoustic Synthesis with Multimodal Flow Matching CVPR 2026

Amandine Brunetto

comment: To appear at CVPR 2026. 23 pages, 16 figures. Project Page: https://amandinebtto.github.io/FLAC/

☆ DiscoPhon: Benchmarking the Unsupervised Discovery of Phoneme Inventories With Discrete Speech Units

Maxime Poli, Manel Khentout, Angelo Ortiz Tandazo, Ewan Dunbar, Emmanuel Chemla, Emmanuel Dupoux

comment: 6 pages, 2 figures. Submitted to Interspeech 2026

☆ ARTT: Augmented Reverberant-Target Training for Unsupervised Monaural Speech Dereverberation

Siqi Song, Fulin Wu, Zhong-Qiu Wang

Due to the absence of clean reference signals and spatial cues, monaural unsupervised speech dereverberation is a challenging ill-posed inverse problem. To realize it, we propose augmented reverberant-target training (ARTT), which consists of two stages. In the first stage, reverberant-target training (RTT) is proposed to first further reverberate the observed reverberant mixture signal, and then train a deep neural network (DNN) to recover the observed reverberant mixture via discriminative training. Although the target signal to fit is reverberant, we find that the resulting DNN can effectively reduce reverberation. In the second stage, an online self-distillation mechanism based on the mean-teacher algorithm is proposed to further improve dereverberation. Evaluation results demonstrate that ARTT achieves strong unsupervised dereverberation performance, significantly outperforming previous baselines.

comment: in submission

☆ Listen First, Then Answer: Timestamp-Grounded Speech Reasoning

Jihoon Jeong, Pooneh Mousavi, Mirco Ravanelli, Cem Subakan

comment: Submitted to Interspeech 2026

♻ ☆ DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment

comment: Published in IEEE Transactions on Audio, Speech and Language Processing (TASLP). Model and code available at: https://github.com/kehanlu/DeSTA2.5-Audio

♻ ☆ Affect Decoding in Phonated and Silent Speech Production from Surface EMG

Simon Pistrosch, Kleanthis Avramidis, Zhao Ren, Tiantian Feng, Jihwan Lee, Monica Gonzalez-Machorro, Anton Batliner, Tanja Schultz, Shrikanth Narayanan, Björn W. Schuller

♻ ☆ Fair-Gate: Fairness-Aware Interpretable Risk Gating for Sex-Fair Voice Biometrics

Yangyang Qu, Todisco Massimiliano, Galdi Chiara, Evans Nicholas

♻ ☆ Group-Aware Partial Model Merging for Children's Automatic Speech Recognition

Thomas Rolland, Alberto Abad

While supervised fine-tuning of adult pre-trained models for children's ASR has shown promise, it often fails to capture group-specific characteristics and variations among children. To address this, we introduce GRoup-Aware PARtial model Merging, a parameter-efficient approach that combines unsupervised clustering, partial fine-tuning, and model merging. Our approach adapts adult-pre-trained models to children by first grouping the children's data based on acoustic similarity. Each group is used to partially fine-tune an adult pre-trained model, and the resulting models are merged at the parameter level. Experiments conducted on the MyST children's speech corpus indicate that GRAPAM achieves a relative WER improvement of 6%, using the same amount of data, outperforming full fine-tuning while training fewer parameters.

comment: Submitted to Interspeech 2026

♻ ☆ MPDR Beamforming for Almost-Cyclostationary Processes

Giovanni Bologni, Martin Bo Møller, Richard Heusdens, Richard C. Hendriks

comment: This work has been submitted to the IEEE for possible publication

♻ ☆ Investigating Faithfulness in Large Audio Language Models

Pooneh Mousavi, Lovenya Jain, Mirco Ravanelli, Cem Subakan

Large Audio Language Models (LALMs) integrate audio encoders with pretrained Large Language Models to perform complex multimodal reasoning tasks. While these models can generate Chain-of-Thought (CoT) explanations, the faithfulness of these reasoning chains remains unclear. In this work, we propose a systematic framework to evaluate CoT faithfulness in LALMs with respect to both the input audio and the final model prediction. We define three criteria for audio faithfulness: hallucination-free, holistic, and attentive listening. We also introduce a benchmark based on both audio and CoT interventions to assess faithfulness. Experiments on Audio Flamingo 3 and Qwen2.5-Omni suggest a potential multimodal disconnect: reasoning often aligns with the final prediction but is not always strongly grounded in the audio and can be vulnerable to hallucinations or adversarial perturbations.

♻ ☆ Evaluating Hallucinations in Audio-Visual Multimodal LLMs with Spoken Queries under Diverse Acoustic Conditions

Hansol Park, Hoseong Ahn, Junwon Moon, Yejin Lee, Kyuhong Shim

comment: Submitted to Interspeech2026

2026-03-18

Sound 10

☆ Modeling Overlapped Speech with Shuffles

Matthew Wiesner, Samuele Cornell, Alexander Polok, Lucas Ondel Yang, Lukáš Burget, Sanjeev Khudanpur

We propose to model parallel streams of data, such as overlapped speech, using shuffles. Specifically, this paper shows how the shuffle product and partial order finite-state automata (FSAs) can be used for alignment and speaker-attributed transcription of overlapped speech. We train using the total score on these FSAs as a loss function, marginalizing over all possible serializations of overlapping sequences at subword, word, and phrase levels. To reduce graph size, we impose temporal constraints by constructing partial order FSAs. We address speaker attribution by modeling (token, speaker) tuples directly. Viterbi alignment through the shuffle product FSA directly enables one-pass alignment. We evaluate performance on synthetic LibriSpeech overlaps. To our knowledge, this is the first algorithm that enables single-pass alignment of multi-talker recordings. All algorithms are implemented using k2 / Icefall.

☆ Zipper-LoRA: Dynamic Parameter Decoupling for Speech-LLM based Multilingual Speech Recognition

Yuxiang Mei, Delai Qiu, Shengping Liu, Jiaen Liang, Yanhua Long

comment: 13 pages, 8 figures

☆ Towards Interpretable Framework for Neural Audio Codecs via Sparse Autoencoders: A Case Study on Accent Information

Shih-Heng Wang, Tiantian Feng, Aditya Kommineni, Thanathai Lertpetchpun, Bowen Yi, Xuan Shi, Shrikanth Narayanan

Neural Audio Codecs (NACs) are widely adopted in modern speech systems, yet how they encode linguistic and paralinguistic information remains unclear. Improving the interpretability of NAC representations is critical for understanding and deploying them in sensitive applications. Hence, we employ Sparse Autoencoders (SAEs) to decompose dense NAC representations into sparse, interpretable activations. In this work, we focus on a challenging paralinguistic attribute-accent-and propose a framework to quantify NAC interpretability. We evaluate four NAC models under 16 SAE configurations using a relative performance index. Our results show that DAC and SpeechTokenizer achieve the highest interpretability. We further reveal that acoustic-oriented NACs encode accent information primarily in activation magnitudes of sparse representations, whereas phonetic-oriented NACs rely more on activation positions, and that low-bitrate EnCodec variants show higher interpretability.

☆ ALIGN: Adversarial Learning for Generalizable Speech Neuroprosthesis

Zhanqi Zhang, Shun Li, Bernardo L. Sabatini, Mikio Aoi, Gal Mishne

Intracortical brain-computer interfaces (BCIs) can decode speech from neural activity with high accuracy when trained on data pooled across recording sessions. In realistic deployment, however, models must generalize to new sessions without labeled data, and performance often degrades due to cross-session nonstationarities (e.g., electrode shifts, neural turnover, and changes in user strategy). In this paper, we propose ALIGN, a session-invariant learning framework based on multi-domain adversarial neural networks for semi-supervised cross-session adaptation. ALIGN trains a feature encoder jointly with a phoneme classifier and a domain classifier operating on the latent representation. Through adversarial optimization, the encoder is encouraged to preserve task-relevant information while suppressing session-specific cues. We evaluate ALIGN on intracortical speech decoding and find that it generalizes consistently better to previously unseen sessions, improving both phoneme error rate and word error rate relative to baselines. These results indicate that adversarial domain alignment is an effective approach for mitigating session-level distribution shift and enabling robust longitudinal BCI decoding.

☆ STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling

Kun Wang, Meng Chen, Junhao Wang, Yuli Wu, Li Lu, Chong Zhang, Peng Cheng, Jiaheng Zhang, Kui Ren

With the widespread deployment of deep-learning-based speech models in security-critical applications, backdoor attacks have emerged as a serious threat: an adversary who poisons a small fraction of training data can implant a hidden trigger that controls the model's output while preserving normal behavior on clean inputs. Existing inference-time defenses are not well suited to the audio domain, as they either rely on trigger over-robustness assumptions that fail on transformation-based and semantic triggers, or depend on properties specific to image or text modalities. In this paper, we propose STEP (Stability-based Trigger Exposure Profiling), a black-box, retraining-free backdoor detector that operates under hard-label-only access. Its core idea is to exploit a characteristic dual anomaly of backdoor triggers: anomalous label stability under semantic-breaking perturbations, and anomalous label fragility under semantic-preserving perturbations. STEP profiles each test sample with two complementary perturbation branches that target these two properties respectively, scores the resulting stability features with one-class anomaly detectors trained on benign references, and fuses the two scores via unsupervised weighting. Extensive experiments across seven backdoor attacks show that STEP achieves an average AUROC of 97.92% and EER of 4.54%, substantially outperforming state-of-the-art baselines, and generalizes across model architectures, speech tasks, an open-set verification scenario, and over-the-air physical-world settings.

☆ MOSS-TTS Technical Report

comment: Project page: https://github.com/OpenMOSS/MOSS-TTS

☆ EgoAdapt: Enhancing Robustness in Egocentric Interactive Speaker Detection Under Missing Modalities

Xinyuan Qian, Xinjia Zhu, Alessio Brutti, Dong Liang

TTM (Talking to Me) task is a pivotal component in understanding human social interactions, aiming to determine who is engaged in conversation with the camera-wearer. Traditional models often face challenges in real-world scenarios due to missing visual data, neglecting the role of head orientation, and background noise. This study addresses these limitations by introducing EgoAdapt, an adaptive framework designed for robust egocentric "Talking to Me" speaker detection under missing modalities. Specifically, EgoAdapt incorporates three key modules: (1) a Visual Speaker Target Recognition (VSTR) module that captures head orientation as a non-verbal cue and lip movement as a verbal cue, allowing a comprehensive interpretation of both verbal and non-verbal signals to address TTM, setting it apart from tasks focused solely on detecting speaking status; (2) a Parallel Shared-weight Audio (PSA) encoder for enhanced audio feature extraction in noisy environments; and (3) a Visual Modality Missing Awareness (VMMA) module that estimates the presence or absence of each modality at each frame to adjust the system response dynamically.Comprehensive evaluations on the TTM benchmark of the Ego4D dataset demonstrate that EgoAdapt achieves a mean Average Precision (mAP) of 67.39% and an Accuracy (Acc) of 62.01%, significantly outperforming the state-of-the-art method by 4.96% in Accuracy and 1.56% in mAP.

♻ ☆ NV-Bench: Benchmark of Nonverbal Vocalization Synthesis for Expressive Text-to-Speech Generation

Qinke Ni, Huan Liao, Dekun Chen, Yuxiang Wang, Zhizheng Wu

While recent text-to-speech (TTS) systems increasingly integrate nonverbal vocalizations (NVs), their evaluations lack standardized metrics and reliable ground-truth references. To bridge this gap, we propose NV-Bench, the first benchmark grounded in a functional taxonomy that treats NVs as communicative acts rather than acoustic artifacts. NV-Bench comprises 1,651 multi-lingual, in-the-wild utterances with paired human reference audio, balanced across 14 NV categories. We introduce a dual-dimensional evaluation protocol: (1) Instruction Alignment, utilizing the proposed paralinguistic character error rate (PCER) to assess controllability, (2) Acoustic Fidelity, measuring the distributional gap to real recordings to assess acoustic realism. We evaluate diverse TTS models and develop two baselines. Experimental results demonstrate a strong correlation between our objective metrics and human perception, establishing NV-Bench as a standardized evaluation framework.

comment: Submit to Interspeech 2026

♻ ☆ Integrated Spoofing-Robust Automatic Speaker Verification via a Three-Class Formulation and LLR

Kai Tan, Lin Zhang, Ruiteng Zhang, Johan Rohdin, Leibny Paola García-Perera, Zexin Cai, Sanjeev Khudanpur, Matthew Wiesner, Nicholas Andrews

Spoofing-robust automatic speaker verification (SASV) aims to integrate automatic speaker verification (ASV) and countermeasure (CM). A popular solution is fusion of independent ASV and CM scores. To better modeling SASV, some frameworks integrate ASV and CM within a single network. However, these solutions are typically bi-encoder based, offer limited interpretability, and cannot be readily adapted to new evaluation parameters without retraining. Based on this, we propose a unified end-to-end framework via a three-class formulation that enables log-likelihood ratio (LLR) inference from class logits for a more interpretable decision pipeline. Experiments show comparable performance to existing methods on ASVSpoof5 and better results on SpoofCeleb. The visualization and analysis also prove that the three-class reformulation provides more interpretability.

comment: Submitted to Interspeech 2026; put on arxiv based on requirement from Interspeech: "Interspeech no longer enforces an anonymity period for submissions." and "For authors that prefer to upload their paper online, a note indicating that the paper was submitted for review to Interspeech should be included in the posting."

♻ ☆ Feature Selection via Graph Topology Inference for Soundscape Emotion Recognition

Samuel Rey, Luca Martino, Roberto San Millan, Eduardo Morgado

Research on soundscapes has shifted the focus of environmental acoustics from noise levels to the perception of sounds, incorporating contextual factors. Soundscape emotion recognition (SER) models perception using a set of features, with arousal and valence commonly regarded as sufficient descriptors of affect. In this work, we blend \emph{graph learning} techniques with a novel \emph{information criterion} to develop a feature selection framework for SER. Specifically, we estimate a sparse graph representation of feature relations using linear structural equation models (SEM) tailored to the widely used Emo-Soundscapes dataset. The resulting graph captures the relations between input features and the two emotional outputs. To determine the appropriate level of sparsity, we propose a novel \emph{generalized elbow detector}, which provides both a point estimate and an uncertainty interval. We conduct an extensive evaluation of our methods, including visualizations of the inferred relations. While several of our findings align with previous studies, the graph representation also reveals a strong connection between arousal and valence, challenging common SER assumptions.

Audio and Speech Processing 10

★ The Silent Thought: Modeling Internal Cognition in Full-Duplex Spoken Dialogue Models via Latent Reasoning

Donghang Wu, Tianyu Zhang, Yuxin Li, Hexin Liu, Chen Chen, Eng Siong Chng, Yoshua Bengio

During conversational interactions, humans subconsciously engage in concurrent thinking while listening to a speaker. Although this internal cognitive processing may not always manifest as explicit linguistic structures, it is instrumental in formulating high-quality responses. Inspired by this cognitive phenomenon, we propose a novel Full-duplex LAtent and Internal Reasoning method named FLAIR that conducts latent thinking simultaneously with speech perception. Unlike conventional "thinking" mechanisms in NLP, which require post-hoc generation, our approach aligns seamlessly with spoken dialogue systems: during the user's speaking phase, it recursively feeds the latent embedding output from the previous step into the next step, enabling continuous reasoning that strictly adheres to causality without introducing additional latency. To enable this latent reasoning, we design an Evidence Lower Bound-based objective that supports efficient supervised finetuning via teacher forcing, circumventing the need for explicit reasoning annotations. Experiments demonstrate the effectiveness of this think-while-listening design, which achieves competitive results on a range of speech benchmarks. Furthermore, FLAIR robustly handles conversational dynamics and attains competitive performance on full-duplex interaction metrics.

☆ Multi-Source Evidence Fusion for Audio Question Answering

Aivo Olev, Tanel Alumäe

Large audio language models (LALMs) can answer questions about speech, music, and environmental sounds, yet their internal reasoning is largely opaque and difficult to validate. We describe TalTech's solution to the Agent Track of the Interspeech 2026 Audio Reasoning Challenge, in which systems are evaluated on reasoning process quality, specifically the factual accuracy, logical soundness, and completeness of their reasoning chains. Our multi-source ensemble pipeline uses two LALMs that generate independent observations, while a separate text-only reasoning model cross-checks these against outputs from 25 acoustic tools organized into reliability tiers. By grounding every inference step in explicit, reliability-tagged evidence, the system produces dense, verifiable reasoning chains. Our system ranked first in the challenge, outperforming all competing systems by a wide margin in challenge's reasoning quality metric.

☆ Robust Nasality Representation Learning for Cleft Palate-Related Velopharyngeal Dysfunction Screening in Real-World Settings

Weixin Liu, Bowen Qu, Amy Stone, Maria E. Powell, Shama Dufresne, Stephane Braun, Izabela Galdyn, Michael Golinko, Bradley Malin, Zhijun Yin, Matthew E. Pontell

Velopharyngeal dysfunction (VPD) is characterized by inadequate velopharyngeal closure during speech and often causes hypernasality and reduced intelligibility. Although speech-based machine learning models can perform well under standardized clinical recording conditions, their performance often drops in real-world settings because of domain shift caused by differences in devices, channels, noise, and room acoustics. To improve robustness, we propose a two-stage framework for VPD screening. First, a nasality-focused speech representation is learned by supervised contrastive pre-training on an auxiliary corpus with phoneme alignments, using oral-context versus nasal-context supervision. Second, the encoder is frozen and used with lightweight classifiers on 0.5-second speech chunks, whose probabilities are aggregated to produce recording-level decisions with a fixed threshold. On an in-domain clinical cohort of 82 subjects, the proposed method achieved perfect recording-level screening performance (macro-F1 = 1.000, accuracy = 1.000). On a separate out-of-domain set of 131 heterogeneous public Internet recordings, large pretrained speech representations degraded substantially, while MFCC was the strongest baseline (macro-F1 = 0.612, accuracy = 0.641). The proposed method achieved the best out-of-domain performance (macro-F1 = 0.679, accuracy = 0.695), improving on the strongest baseline under the same evaluation protocol. These results suggest that learning a nasality-focused representation before clinical classification can reduce sensitivity to recording artifacts and improve robustness for deployable speech-based VPD screening.

comment: 2 figures. Machine learning for speech-based VPD screening under domain shift

☆ Uncertainty Quantification and Risk Control for Multi-Speaker Sound Source Localization

Vadim Rozenfeld, Bracha Laufer Goldshtein

Reliable Sound Source Localization (SSL) plays an essential role in many downstream tasks, where informed decision making depends not only on accurate localization but also on the confidence in each estimate. This need for reliability becomes even more pronounced in challenging conditions, such as reverberant environments and multi-source scenarios. However, existing SSL methods typically provide only point estimates, offering limited or no Uncertainty Quantification (UQ). We leverage the Conformal Prediction (CP) framework and its extensions for controlling general risk functions to develop two complementary UQ approaches for SSL. The first assumes that the number of active sources is known and constructs prediction regions that cover the true source locations. The second addresses the more challenging setting where the source count is unknown, first reliably estimating the number of active sources and then forming corresponding prediction regions. We evaluate the proposed methods on extensive simulations and real-world recordings across varying reverberation levels and source configurations. Results demonstrate reliable finite-sample guarantees and consistent performance for both known and unknown source-count scenarios, highlighting the practical utility of the proposed frameworks for uncertainty-aware SSL.

comment: 13 pages, 4 figures. Code available at: https://github.com/vadimroz/UQ_in_multi_SSL

☆ Neuron-Level Emotion Control in Speech-Generative Large Audio-Language Models

Xiutian Zhao, Ismail Rasim Ulgen, Philipp Koehn, Björn Schuller, Berrak Sisman

Large audio-language models (LALMs) can produce expressive speech, yet reliable emotion control remains elusive: conversions often miss the target affect and may degrade linguistic fidelity through refusals, hallucinations, or paraphrase. We present, to our knowledge, the first neuron-level study of emotion control in speech-generative LALMs and demonstrate that compact emotion-sensitive neurons (ESNs) are causally actionable, enabling training-free emotion steering at inference time. ESNs are identified via success-filtered activation aggregation enforcing both emotion realization and content preservation. Across three LALMs (Qwen2.5-Omni-7B, MiniCPM-o 4.5, Kimi-Audio), ESN interventions yield emotion-specific gains that generalize to unseen speakers and are supported by automatic and human evaluation. Controllability depends on selector design, mask sparsity, filtering, and intervention strength. Our results establish a mechanistic framework for training-free emotion control in speech generation.

comment: 11 pages, 10 figures

☆ Modeling Overlapped Speech with Shuffles

Matthew Wiesner, Samuele Cornell, Alexander Polok, Lucas Ondel Yang, Lukáš Burget, Sanjeev Khudanpur

♻ ☆ NV-Bench: Benchmark of Nonverbal Vocalization Synthesis for Expressive Text-to-Speech Generation

Qinke Ni, Huan Liao, Dekun Chen, Yuxiang Wang, Zhizheng Wu

comment: Submit to Interspeech 2026

♻ ☆ Integrated Spoofing-Robust Automatic Speaker Verification via a Three-Class Formulation and LLR

Kai Tan, Lin Zhang, Ruiteng Zhang, Johan Rohdin, Leibny Paola García-Perera, Zexin Cai, Sanjeev Khudanpur, Matthew Wiesner, Nicholas Andrews

♻ ☆ Feature Selection via Graph Topology Inference for Soundscape Emotion Recognition

Samuel Rey, Luca Martino, Roberto San Millan, Eduardo Morgado

♻ ☆ Towards Inclusive Communication: A Unified Framework for Generating Spoken Language from Sign, Lip, and Audio

Jeong Hun Yeo, Hyeongseop Rha, Sungjune Park, Junil Won, Yong Man Ro

2026-03-17

Sound 16

☆ Making Separation-First Multi-Stream Audio Watermarking Feasible via Joint Training

Houmin Sun, Zi Hu, Linxi Li, Yechen Wang, Liwei Jin, Ming Li

Modern audio is created by mixing stems from different sources, raising the question: can we independently watermark each stem and recover all watermarks after separation? We study a separation-first, multi-stream watermarking framework-embedding distinct information into stems using unique keys but a shared structure, mixing, separating, and decoding from each output. A naive pipeline (robust watermarking + off-the-shelf separation) yields poor bit recovery, showing robustness to generic distortions does not ensure robustness to separation artifacts. To enable this, we jointly train the watermark system and the separator in an end-to-end manner, encouraging the separator to preserve watermark cues while adapting embedding to separation-specific distortions. Experiments on speech+music and vocal+accompaniment mixtures show substantial gains in post-separation recovery while maintaining perceptual quality.

☆ Evaluating Latent Space Structure in Timbre VAEs: A Comparative Study of Unsupervised, Descriptor-Conditioned, and Perceptual Feature-Conditioned Models

Joseph Cameron, Alan Blackwell

We present a comparative evaluation of latent space organization in three Variational Autoencoders (VAEs) for musical timbre generation: an unsupervised VAE, a descriptor-conditioned VAE, and a VAE conditioned on continuous perceptual features from the AudioCommons timbral models. Using a curated dataset of electric guitar sounds labeled with 19 semantic descriptors across four intensity levels, we assess each model's latent structure with a suite of clustering and interpretability metrics. These include silhouette scores, timbre descriptor compactness, pitch-conditional separation, trajectory linearity, and cross-pitch consistency. Our findings show that conditioning on perceptual features yields a more compact, discriminative, and pitch-invariant latent space, outperforming both the unsupervised and discrete descriptor-conditioned models. This work highlights the limitations of one-hot semantic conditioning and provides methodological tools for evaluating timbre latent spaces, contributing to the development of more controllable and interpretable generative audio models.

comment: 5 pages, 1 figure, 1 table

☆ A Semantic Timbre Dataset for the Electric Guitar

Joseph Cameron, Alan Blackwell

Understanding and manipulating timbre is central to audio synthesis, yet this remains under-explored in machine learning due to a lack of annotated datasets linking perceptual timbre dimensions to semantic descriptors. We present the Semantic Timbre Dataset, a curated collection of monophonic electric guitar sounds, each labeled with one of 19 semantic timbre descriptors and corresponding magnitudes. These descriptors were derived from a qualitative analysis of physical and virtual guitar effect units and applied systematically to clean guitar tones. The dataset bridges perceptual timbre and machine learning representations, supporting learning for timbre control and semantic audio generation. We validate the dataset by training a variational autoencoder (VAE) on its latent space and evaluating it using human perceptual judgments and descriptor classifiers. Results show that the VAE captures timbral structure and enables smooth interpolation across descriptors. We release the dataset, code, and evaluation protocols to support timbre-aware generative AI research.

comment: 5 pages, 7 figures, 2 tables

☆ HRTF-guided Binaural Target Speaker Extraction with Real-World Validation

Yoav Ellinson, Sharon Gannot

This paper presents a Head-Related Transfer Function (HRTF)-guided framework for binaural Target Speaker Extraction (TSE) from mixtures of concurrent sources. Unlike conventional TSE methods based on Direction of Arrival (DOA) estimation or enrollment signals, which often distort perceived spatial location, the proposed approach leverages the listener's HRTF as an explicit spatial prior. The proposed framework is built upon a multi-channel deep blind source separation backbone, adapted to the binaural TSE setting. It is trained on measured HRTFs from a diverse population, enabling cross-listener generalization rather than subject-specific tuning. By conditioning the extraction on HRTF-derived spatial information, the method preserves binaural cues while enhancing speech quality and intelligibility. The performance of the proposed framework is validated through simulations and real recordings obtained from a head and torso simulator (HATS).

comment: Submitted to Interspeech 2026

☆ CAST-TTS: A Simple Cross-Attention Framework for Unified Timbre Control in TTS

Zihao Zheng, Wen Wu, Chao Zhang, Mengyue Wu, Xuenan Xu

Current Text-to-Speech (TTS) systems typically use separate models for speech-prompted and text-prompted timbre control. While unifying both control signals into a single model is desirable, the challenge of cross-modal alignment often results in overly complex architectures and training objective. To address this challenge, we propose CAST-TTS, a simple yet effective framework for unified timbre control. Features are extracted from speech prompts and text prompts using pre-trained encoders. The multi-stage training strategy efficiently aligns the speech and projected text representations within a shared embedding space. A single cross-attention mechanism then allows the model to use either of these representations to control the timbre. Extensive experiments validate that the unified cross-attention mechanism is critical for achieving high-quality synthesis. CAST-TTS achieves performance comparable to specialized single-input models while operating within a unified architecture. The demo page can be accessed at https://HiRookie9.github.io/CAST-TTS-Page.

comment: Submitted to Interspeech 2026

☆ Robust Generative Audio Quality Assessment: Disentangling Quality from Spurious Correlations ICME 2026

Kuan-Tang Huang, Chien-Chun Wang, Cheng-Yeh Yang, Hung-Shin Lee, Hsin-Min Wang, Berlin Chen

The rapid proliferation of AI-Generated Content (AIGC) has necessitated robust metrics for perceptual quality assessment. However, automatic Mean Opinion Score (MOS) prediction models are often compromised by data scarcity, predisposing them to learn spurious correlations-- such as dataset-specific acoustic signatures-- rather than generalized quality features. To address this, we leverage domain adversarial training (DAT) to disentangle true quality perception from these nuisance factors. Unlike prior works that rely on static domain priors, we systematically investigate domain definition strategies ranging from explicit metadata-driven labels to implicit data-driven clusters. Our findings reveal that there is no "one-size-fits-all" domain definition; instead, the optimal strategy is highly dependent on the specific MOS aspect being evaluated. Experimental results demonstrate that our aspect-specific domain strategy effectively mitigates acoustic biases, significantly improving correlation with human ratings and achieving superior generalization on unseen generative scenarios.

comment: Accepted to IEEE ICME 2026

☆ Diffusion Models for Joint Audio-Video Generation

Alejandro Paredes La Torre

Multimodal generative models have shown remarkable progress in single-modality video and audio synthesis, yet truly joint audio-video generation remains an open challenge. In this paper, I explore four key contributions to advance this field. First, I release two high-quality, paired audio-video datasets. The datasets consisting on 13 hours of video-game clips and 64 hours of concert performances, each segmented into consistent 34-second samples to facilitate reproducible research. Second, I train the MM-Diffusion architecture from scratch on our datasets, demonstrating its ability to produce semantically coherent audio-video pairs and quantitatively evaluating alignment on rapid actions and musical cues. Third, I investigate joint latent diffusion by leveraging pretrained video and audio encoder-decoders, uncovering challenges and inconsistencies in the multimodal decoding stage. Finally, I propose a sequential two-step text-to-audio-video generation pipeline: first generating video, then conditioning on both the video output and the original prompt to synthesize temporally synchronized audio. My experiments show that this modular approach yields high-fidelity generations of audio video generation.

☆ Towards the Vision-Sound-Language-Action Paradigm: The HEAR Framework for Sound-Centric Manipulation

Chang Nie, Tianchen Deng, Guangming Wang, Zhe Liu, Hesheng Wang

While recent Vision-Language-Action (VLA) models have begun to incorporate audio, they typically treat sound as static pre-execution prompts or focus exclusively on human speech. This leaves a significant gap in real-time, sound-centric manipulation where fleeting environmental acoustics provide critical state verification during task execution. Consequently, key sounds are easily missed due to low-frequency updates or system latency. This problem is exacerbated by action chunking with open-loop execution, which creates a Blind Execution Interval where acoustic events are lost between discrete audio observation windows. Recognizing the necessity of continuous auditory awareness, we formalize Vision-Sound-Language-Action (VSLA) as a continuous control paradigm conditioned on vision, streaming audio, language, and proprioception under delayed decision loops. As an instantiation, we introduce HEAR, a VSLA framework integrating four components: (i) a streaming Historizer to maintain a compact, causal audio context across execution gaps; (ii) an Envisioner adapted from omni foundation models to reason over multi-sensory inputs; (iii) an Advancer, formulated as an audio world model, to learn temporal dynamics by predicting near-future audio codes; and (iv) a flow-matching Realizer policy to generate smooth action chunks. To address the scarcity of pretraining data and evaluations for VSLA, we construct OpenX-Sound for pretraining, alongside HEAR-Bench, the first sound-centric manipulation benchmark with strict causal timing rules. Our results suggest that robust sound-centric manipulation necessitates causal persistence and explicit temporal learning. This framework provides a practical step toward multi-sensory foundation models for embodied agents, enabling robots to perceive and interact with dynamic environments. Code and videos are available at https://hear.irmv.top.

☆ Over-the-air White-box Attack on the Wav2Vec Speech Recognition Neural Network

Protopopov Alexey

Automatic speech recognition systems based on neural networks are vulnerable to adversarial attacks that alter transcriptions in a malicious way. Recent works in this field have focused on making attacks work in over-the-air scenarios, however such attacks are typically detectable by human hearing, limiting their potential applications. In the present work we explore different approaches of making over-the-air attacks less detectable, as well as the impact these approaches have on the attacks' effectiveness.

comment: 9 pages, 5 figures, 1 table

☆ CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization CVPR 2026

Liangbin Huang, Xiaohua Liao, Chaoqun Cui, Shijing Wang, Zhaolong Huang, Yanlong Du, Wenji Mao

Traditional speaker diarization systems have primarily focused on constrained scenarios such as meetings and interviews, where the number of speakers is limited and acoustic conditions are relatively clean. To explore open-world speaker diarization, we extend this task to the visual media domain, encompassing complex audiovisual programs such as films and TV series. This new setting introduces several challenges, including long-form video understanding, a large number of speakers, cross-modal asynchrony between audio and visual cues, and uncontrolled in-the-wild variability. To address these challenges, we propose Cinematic Speaker Registration & Diarization (CineSRD), a unified multimodal framework that leverages visual, acoustic, and linguistic cues from video, speech, and subtitles for speaker annotation. CineSRD first performs visual anchor clustering to register initial speakers and then integrates an audio language model for speaker turn detection, refining annotations and supplementing unregistered off-screen speakers. Furthermore, we construct and release a dedicated speaker diarization benchmark for visual media that includes Chinese and English programs. Experimental results demonstrate that CineSRD achieves superior performance on the proposed benchmark and competitive results on conventional datasets, validating its robustness and generalizability in open-world visual media settings.

comment: Accepted to CVPR 2026

☆ DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language Models

Jiaqi Xiong, Yunjia Qi, Qi Cao, Yu Zheng, Weisheng Xu, Ziteng Wang, Ruofan Liao, Yutong Zhang, Sichen Liu

comment: 14 pages,6 figures

♻ ☆ Building Enterprise Realtime Voice Agents from Scratch: A Technical Tutorial

Jielin Qiu, Zixiang Chen, Liangwei Yang, Ming Zhu, Zhiwei Liu, Juntao Tan, Wenting Zhao, Rithesh Murthy, Roshan Ram, Akshara Prabhakar, Shelby Heinecke, Caiming Xiong, Silvio Savarese, Huan Wang

We present a technical tutorial for building enterprise-grade realtime voice agents from first principles. While end-to-end speech-to-speech models may ultimately provide the best latency for voice agents, fully self-hosted end-to-end solutions are not yet available. We evaluate the closest candidate, Qwen3-Omni, across three configurations: its cloud-only DashScope Realtime API achieves $\sim$702ms audio-to-audio latency with streaming, but is not self-hostable; its local vLLM deployment supports only the Thinker (text generation from audio, 516ms), not the Talker (audio synthesis); and its local Transformers deployment runs the full pipeline but at $\sim$146s -- far too slow for realtime. The cascaded streaming pipeline (STT $\rightarrow$ LLM $\rightarrow$ TTS) therefore remains the practical architecture for self-hosted realtime voice agents, and the focus of this tutorial. We build a complete voice agent using Deepgram (streaming STT), vLLM-served LLMs with function calling (streaming text generation), and ElevenLabs (streaming TTS), achieving a measured time-to-first-audio of 755ms (best case 729ms) with full function calling support. We release the full codebase as a 9-chapter progressive tutorial with working, tested code for every component.

♻ ☆ LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement

Chih-Ning Chen, Jen-Cheng Hou, Hsin-Min Wang, Shao-Yi Chien, Yu Tsao, Fan-Gang Zeng

In existing Audio-Visual Speech Enhancement (AVSE) methods, objectives such as Scale-Invariant Signal-to-Noise Ratio (SI-SNR) and Mean Squared Error (MSE) are widely used; however, they often correlate poorly with perceptual quality and provide limited interpretability for optimization. This work proposes a reinforcement learning-based AVSE framework with a Large Language Model (LLM)-based interpretable reward model. An audio LLM generates natural language descriptions of enhanced speech, which are converted by a sentiment analysis model into a 1-5 rating score serving as the PPO reward for fine-tuning a pretrained AVSE model. Compared with scalar metrics, LLM-generated feedback is semantically rich and explicitly describes improvements in speech quality. Experiments on the 4th COG-MHEAR AVSE Challenge (AVSEC-4) dataset show that the proposed method outperforms a supervised baseline and a DNSMOS-based RL baseline in PESQ, STOI, neural quality metrics, and subjective listening tests.

comment: 6 pages, 4 figures, submitted to Interspeech 2026

♻ ☆ When Silence Matters: The Impact of Irrelevant Audio on Text Reasoning in Large Audio-Language Models ICASSP 2026

Chen-An Li, Tzu-Han Lin, Hung-yi Lee

Large audio-language models (LALMs) unify speech and text processing, but their robustness in noisy real-world settings remains underexplored. We investigate how irrelevant audio, such as silence, synthetic noise, and environmental sounds, affects text reasoning tasks where audio is unnecessary. Across three text-based benchmarks, we find that even non-informative audio reduces accuracy and increases prediction volatility; the severity of interference scales with longer durations, higher amplitudes, and elevated decoding temperatures. Silence, often assumed neutral, destabilizes outputs as strongly as synthetic noise. While larger models show greater resilience, vulnerabilities persist across all evaluated systems. We further test mitigation strategies and find that prompting shows limited effectiveness, whereas self-consistency improves stability at the cost of increased computation. Our results reveal cross-modal interference as a key robustness challenge and highlight the need for efficient fusion strategies that preserve reasoning performance in the presence of irrelevant inputs.

comment: Accepted to ICASSP 2026

♻ ☆ DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization CVPR 2026

Ngoc-Son Nguyen, Thanh V. T. Tran, Jeongsoo Choi, Hieu-Nghia Huynh-Nguyen, Truong-Son Hy, Van Nguyen

comment: Accepted at CVPR 2026 Findings

♻ ☆ VorTEX: Various overlap ratio for Target speech EXtraction

Ro-hoon Oh, Jihwan Seol, Bugeun Kim

comment: arXiv Preprint

Audio and Speech Processing 14

☆ HRTF-guided Binaural Target Speaker Extraction with Real-World Validation

Yoav Ellinson, Sharon Gannot

comment: Submitted to Interspeech 2026

☆ RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based Recovery

Abhishek Kumar, Aashraya Sachdeva

Entity recognition in Automatic Speech Recognition (ASR) is challenging for rare and domain-specific terms. In domains such as finance, medicine, and air traffic control, these errors are costly. If the entities are entirely absent from the ASR output, post-ASR correction becomes difficult. To address this, we introduce RECOVER, an agentic correction framework that serves as a tool-using agent. It leverages multiple hypotheses as evidence from ASR, retrieves relevant entities, and applies Large Language Model (LLM) correction under constraints. The hypotheses are used using different strategies, namely, 1-Best, Entity-Aware Select, Recognizer Output Voting Error Reduction (ROVER) Ensemble, and LLM-Select. Evaluated across five diverse datasets, it achieves 8-46% relative reductions in entity-phrase word error rate (E-WER) and increases recall by up to 22 percentage points. The LLM-Select achieves the best overall performance in entity correction while maintaining overall WER.

comment: Under review. Submitted to Interspeech 2026

☆ CAST-TTS: A Simple Cross-Attention Framework for Unified Timbre Control in TTS

Zihao Zheng, Wen Wu, Chao Zhang, Mengyue Wu, Xuenan Xu

comment: Submitted to Interspeech 2026

☆ Speakers Localization Using Batch EM In Unfolding Neural Network ICSE

Rina Veler, Sharon Gannot

We propose an interpretable Batch-EM Unfolded Network for robust speaker localization. By embedding the iterative EM procedure within an encoder-EM-decoder architecture, the method mitigates initialization sensitivity and improves convergence. Experiments show superior accuracy and robustness over the classical Batch-EM in reverberant conditions.

comment: 3 pages, 1 figure, ICSEE 2026

☆ Robust Generative Audio Quality Assessment: Disentangling Quality from Spurious Correlations ICME 2026

Kuan-Tang Huang, Chien-Chun Wang, Cheng-Yeh Yang, Hung-Shin Lee, Hsin-Min Wang, Berlin Chen

comment: Accepted to IEEE ICME 2026

☆ Collecting Prosody in the Wild: A Content-Controlled, Privacy-First Smartphone Protocol and Empirical Evaluation

Timo K. Koch, Florian Bemmann, Ramona Schoedel, Markus Buehner, Clemens Stachl

Collecting everyday speech data for prosodic analysis is challenging due to the confounding of prosody and semantics, privacy constraints, and participant compliance. We introduce and empirically evaluate a content-controlled, privacy-first smartphone protocol that uses scripted read-aloud sentences to standardize lexical content (including prompt valence) while capturing natural variation in prosodic delivery. The protocol performs on-device prosodic feature extraction, deletes raw audio immediately, and transmits only derived features for analysis. We deployed the protocol in a large study (N = 560; 9,877 recordings), evaluated compliance and data quality, and conducted diagnostic prediction tasks on the extracted features, predicting speaker sex and concurrently reported momentary affective states (valence, arousal). We discuss implications and directions for advancing and deploying the protocol.

comment: Submitted to Interspeech 2026

☆ Shared Representation Learning for Reference-Guided Targeted Sound Detection ICASSP 2026

Shubham Gupta, Adarsh Arigala, B. R. Dilleswari, Sri Rama Murty Kodukula

Human listeners exhibit the remarkable ability to segregate a desired sound from complex acoustic scenes through selective auditory attention, motivating the study of Targeted Sound Detection (TSD). The task requires detecting and localizing a target sound in a mixture when a reference audio of that sound is provided. Prior approaches, rely on generating a sound-discriminative conditional embedding vector for the reference and pairing it with a mixture encoder, jointly optimized with a multi-task learning approach. In this work, we propose a unified encoder architecture that processes both the reference and mixture audio within a shared representation space, promoting stronger alignment while reducing architectural complexity. This design choice not only simplifies the overall framework but also enhances generalization to unseen classes. Following the multi-task training paradigm, our method achieves substantial improvements over prior approaches, surpassing existing methods and establishing a new state-of-the-art benchmark for targeted sound detection, with a segment-level F1 score of 83.15% and an overall accuracy of 95.17% on the URBAN-SED dataset.

comment: Accepted to IEEE ICASSP 2026

☆ Over-the-air White-box Attack on the Wav2Vec Speech Recognition Neural Network

Protopopov Alexey

comment: 9 pages, 5 figures, 1 table

☆ CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization CVPR 2026

Liangbin Huang, Xiaohua Liao, Chaoqun Cui, Shijing Wang, Zhaolong Huang, Yanlong Du, Wenji Mao

comment: Accepted to CVPR 2026

☆ DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language Models

Jiaqi Xiong, Yunjia Qi, Qi Cao, Yu Zheng, Weisheng Xu, Ziteng Wang, Ruofan Liao, Yutong Zhang, Sichen Liu

comment: 14 pages,6 figures

♻ ☆ LLM-Guided Reinforcement Learning for Audio-Visual Speech Enhancement

Chih-Ning Chen, Jen-Cheng Hou, Hsin-Min Wang, Shao-Yi Chien, Yu Tsao, Fan-Gang Zeng

comment: 6 pages, 4 figures, submitted to Interspeech 2026

♻ ☆ Code-switching Speech Recognition Under the Lens: Model- and Data-Centric Perspectives

Hexin Liu, Haoyang Zhang, Qiquan Zhang, Xiangyu Zhang, Dongyuan Shi, Eng Siong Chng, Haizhou Li

Code-switching automatic speech recognition (CS-ASR) presents unique challenges due to language confusion introduced by spontaneous intra-sentence switching and accent bias that blurs the phonetic boundaries. Although the constituent languages may be individually high-resource, the scarcity of annotated code-switching data further compounds these challenges. In this paper, we systematically analyze CS-ASR from both model-centric and data-centric perspectives. By comparing state-of-the-art algorithmic methods, including language-specific processing and auxiliary language-aware multi-task learning, we discuss their varying effectiveness across datasets with different linguistic characteristics. On the data side, we first investigate TTS as a data augmentation method. By varying the textual characteristics and speaker accents, we analyze the impact of language confusion and accent bias on CS-ASR. To further mitigate data scarcity and enhance textual diversity, we propose a prompting strategy by simplifying the equivalence constraint theory (SECT) to guide large language models (LLMs) in generating linguistically valid code-switching text. The proposed SECT outperforms existing methods in ASR performance and linguistic quality assessments, generating code-switching text that more closely resembles real-world code-switching text. When used to generate speech-text pairs via TTS, SECT proves effective in improving CS-ASR performance. Our analysis of both model- and data-centric methods underscores that effective CS-ASR requires strategies to be carefully aligned with the specific linguistic characteristics of the code-switching data.

comment: 14 pages, 4 figures, 10 tables, accepted to IEEE TASLP. Copyright has been transferred to IEEE

♻ ☆ Time-Layer Adaptive Alignment for Speaker Similarity in Flow-Matching Based Zero-Shot TTS INTERSPEECH 2026

Haoyu Li, Mingyang Han, Yu Xi, Dongxiao Wang, Hankun Wang, Haoxiang Shi, Boyu Li, Jun Song, Bo Zheng, Shuai Wang, Kai Yu

Flow-Matching (FM)-based zero-shot text-to-speech (TTS) systems exhibit high-quality speech synthesis and robust generalization capabilities. However, the speaker representation ability of such systems remains underexplored, primarily due to the lack of explicit speaker-specific supervision in the FM framework. To this end, we conduct an empirical analysis of speaker information distribution and reveal its non-uniform allocation across time steps and network layers, underscoring the need for adaptive speaker alignment. Accordingly, we propose Time-Layer Adaptive Speaker Alignment (TLA-SA), a strategy that enhances speaker consistency by jointly leveraging temporal and hierarchical variations. Experimental results show that TLA-SA substantially improves speaker similarity over baseline systems on both research- and industrial-scale datasets and generalizes well across diverse model architectures, including decoder-only language model (LM)-based and free TTS systems. A demo is provided.

comment: Submitted to INTERSPEECH 2026

♻ ☆ Do You Hear What I Mean? Quantifying the Instruction-Perception Gap in Instruction-Guided Expressive Text-To-Speech Systems ICASSP 2026

Yi-Cheng Lin, Huang-Cheng Chou, Tzu-Chieh Wei, Kuan-Yu Chen, Hung-yi Lee

Instruction-guided text-to-speech (ITTS) enables users to control speech generation through natural language prompts, offering a more intuitive interface than traditional TTS. However, the alignment between user style instructions and listener perception remains largely unexplored. This work first presents a perceptual analysis of ITTS controllability across two expressive dimensions (adverbs of degree and graded emotion intensity) and collects human ratings on speaker age and word-level emphasis attributes. To comprehensively reveal the instruction-perception gap, we provide a data collection with large-scale human evaluations, named Expressive VOice Control (E-VOC) corpus. Furthermore, we reveal that (1) gpt-4o-mini-tts is the most reliable ITTS model with great alignment between instruction and generated utterances across acoustic dimensions. (2) The 5 analyzed ITTS systems tend to generate Adult voices even when the instructions ask to use child or Elderly voices. (3) Fine-grained control remains a major challenge, indicating that most ITTS systems have substantial room for improvement in interpreting slightly different attribute instructions.

comment: Accepted to ICASSP 2026