Daily Papers — 2026-09-24

74 papers on audio, speech, music, and acoustics.

1. LOGIC: Efficient and Robust Contextual Biasing for Speech LLMs via Logit-Space Integration

Authors: Peidong Wang, Jian Xue, Jinyu Li

Categories: cs.AI, cs.CL, cs.SD

Recognizing entity phrases remains a critical challenge for speech large language models. Existing prompting methods lack an explicit decoding-time biasing weight, limiting their controllability. Generative error correction methods can introduce hallucinated over-corrections. To address these limitations, we propose LOGIC (logit-space integration for contextual biasing), a robust framework operating directly in the logit space. By decoupling context injection from input processing, LOGIC enables explicit control over the biasing strength. Extensive experiments with an open-source speech large language model across 11 locales demonstrate that LOGIC achieves an average 9% relative reduction in entity word error rate, with an average false alarm rate increase of 0.3% and a 2.8% relative runtime overhead. When combined with prompting, LOGIC can reduce entity word error rate by 5% relative to the prompt-only method.

2. Do Audio Language Models Hear and Read Distinctive Features Alike?

Authors: Yuanhao Chen, Peter Chin

Categories: cs.CL, cs.LG, cs.SD, stat.AP

Audio language models pass speech and text through a single decoder. We ask whether that decoder represents a distinctive feature in the same direction when a phoneme is heard and when it is read. For minimal pairs of phonemes differing in one feature, we take the offset between the two members’ mean representations. Averaging those offsets gives a direction for each stream, and we measure the cosine between the two. Because the two streams already agree about arbitrary phoneme pairs, we compare every measure against a reference built from random pairings rather than against zero. We apply this to 6 models, 7 features and 15 languages from 11 families. Only voicing in the two Qwen2.5-Omni models exceeds that reference after correction for multiple testing, and the reference varies by a factor of seven between models. In three of the six models, voicing has one direction in audio across the 14 languages with enough minimal pairs to measure it, and every language pair agrees in two of them. The model family, not the model size, predicts which stream represents a feature.

3. A Native-Reference Phone-Class Geometry for Second-Language Pronunciation Analysis

Authors: Tina Raissi, Nhan Phan, Chenxiao Wang, Mikko Kurimo

Categories: cs.CL, cs.SD

Automatic speaking assessment systems can provide holistic proficiency scores, but often lack interpretable measures that characterize pronunciation quality. We propose a native-reference phone-class geometry for measuring second language (L2) pronunciation deviation without requiring pronunciation labels, read-aloud prompts, or matched recordings of the same text from native and L2 speakers. Given a native speech corpus, we average frame-level self-supervised representations for each context-dependent phone-class and use singular value decomposition (SVD) to derive a compact native-reference coordinate system. For each L2 utterance, we compute the corresponding averages and project them into the native-reference space. We then demonstrate that the distances between L2 and native-reference coordinates for matched phone-classes show consistent negative correlations with holistic speaking proficiency on the Dev subset of the Speak and Improve Corpus 2025 (Spearman’s $ρ!=!-0.53$) and with pronunciation quality on the learner subset of the English Read by Japanese Students dataset ($ρ!=!-0.34$). These findings suggest that the proposed geometry captures acoustic-phonetic information relevant for proficiency rating while remaining applicable to spontaneous L2 speech without matched native recordings.

4. An Evaluation Framework for Structured Audio Captions Validated by Controlled Perturbations

Authors: Liang-Yuan Wu, Sripathi Sridhar, Mark Cartwright, Magdalena Fuentes

Categories: cs.CL, cs.SD

Recent advances in automated audio captioning (AAC) are driving a shift from monolithic sentences toward structured formats that disentangle acoustic and semantic properties, such as timestamped captions for different sound events. Such representations can support faceted sound search for creators and richer access to auditory information for Deaf and Hard of Hearing people. Yet, it remains unclear how to meaningfully evaluate these hybrid, structured captions. We propose an evaluation framework for structured audio descriptions, spanning five complementary axes: tag sets, descriptions, reasoning, numeric measurements, and spectral profiles. The framework combines large language model (LLM) judges for semantic fields with deterministic metrics for temporal and acoustic attributes. To validate these metrics, we introduce controlled perturbations that apply typed, graded changes to ground-truth annotations. Results show that the proposed metrics remain robust to meaning-preserving paraphrases while responding to genuine semantic and acoustic corruptions, enabling more reliable evaluation of structured captions.

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

Authors: Maxime Poli, Manel Khentout, Angelo Ortiz Tandazo, Ewan Dunbar, Emmanuel Chemla et al.

Categories: cs.CL, cs.SD, eess.AS

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.

6. A Training Criterion with Token-Level Tolerance to Transcription Ambiguity for Automatic Speech Recognition

Authors: Saurabh Kumar, Diptiman Mohanta, Prasanta Kumar Ghosh

Categories: cs.CL, eess.AS

Automatic speech recognition is typically trained assuming that the reference transcript is the only valid labeling of an utterance, yet even nominally verbatim transcripts contain localized differences in pronunciation, spelling, or lexical realization that the acoustics do not uniquely determine. Omni-temporal Classification (OTC) tolerates such noise by adding wildcard paths to the connectionist temporal classification (CTC) alignment graph, but its word-level arcs are too coarse, since bypassing one unsupported token discards supervision for the whole word. We move wildcard arcs to token granularity so unsupported tokens can be bypassed while the rest of the word stays supervised, and we combine token- and word-level arcs as complementary escape paths. Across 19 languages and three corpora, token-level OTC improves over CTC on all 25 tasks. We also replace epoch-indexed relaxation of the wildcard weights with a predictive-entropy-indexed schedule, which performs comparably while reducing dependence on training length. Combining this schedule with the hybrid graph gives the lowest mean word error rate (WER) on every corpus and a 9.45% average relative WER reduction over CTC. Independent validator transcriptions show that token-level models place significantly more wildcard-bypass probability than CTC on disputed characters, indicating that token-level tolerance targets localized transcript ambiguity.

7. Proactive for Uncertainty: Cause-Aware Error Diagnosis and Interactive Clarification for Spoken Dialogue Systems

Authors: Yizhou Peng, Ziyang Ma, Changsong Liu, Yi-Wen Chao, Xie Chen et al.

Categories: cs.CL, eess.AS

Cascaded Automatic Speech Recognition - Large Language Model (ASR-LLM) pipelines remain popular for industrial Spoken Dialogue Systems (SDS), primarily because their decoupled design ensures perceptual verifiability. However, cascaded systems suffer from error propagation, as transcription failures inevitably cascade to subsequent components, thereby degrading the final interaction quality. Although ASR confidence scores offer a simple filter for unreliable inputs, this approach is fundamentally limited because it typically fails to detect deletion errors or to distinguish between acoustic (inability to hear clearly) and linguistic (inability to understand) mismatches, both of which require targeted recovery strategies. In this paper, we propose a cause-aware error recovery paradigm that fundamentally rethinks robustness in SDS. Unlike traditional confidence filtering, we introduce a suite of small precision-focused detectors that exploit deep ASR latent representations to disentangle token-level errors into perception, comprehension, and deletion failures. This fine-grained diagnostic intelligence empowers the LLM to orchestrate targeted, multi-turn clarification strategies, effectively transforming ambiguous signals into seamless user interactions. Experimental results validate the precision of our approach, which more than doubles the recall on domain-shift errors (57.96% vs. 23.66%) compared to baselines. Crucially, this diagnostic precision yields up to a 31% reduction in WER and a 19% improvement on the downstream task across diverse accents, distortions, and domains.

8. AV-GRPO: Modality-Anchored Decoupling Diffusion Reinforcement Learning for Joint Audio-Video Generation

Authors: Zhiyu Xu, Weilong Yan, Yufei Shi, Shiyang Li, Yihao Liu et al.

Categories: cs.CV, cs.SD

Recent years have witnessed major progress in joint audio-video generation. Existing models still suffer from limited per-modality fidelity, insufficient text-modality alignment and weak cross-modal synchronization. While reinforcement-learning post-training offers a promising remedy, directly adapting it to joint audio-video generation is challenging. Heterogeneous multimodal rewards entangle learning signals and complicate credit assignment. Joint optimization of two modality towers is computationally expensive given their divergent dynamics. Moreover, synchronization evaluation difficulty depends on paired samples, preventing fair reward comparisons. We propose AV-GRPO, a modality-anchored online diffusion RL framework, and 5DAV, a decoupled, difficulty-controllable training dataset. AV-GRPO includes three key modules: (1) modality-anchored rollouts to disentangle learning signals and stabilize difficulty; (2) trajectory-locked frozen-tower optimization to reduce cost and reassign credit; (3) adaptive objectives and perturbation strengths tailored to modality-specific dynamics. This converts coupled multimodal preference learning into unimodal subproblems for precise reward attribution and better synchronization. Our 5DAV dataset decouples samples across five dimensions for systematic training. Experiments on JavisBench and VABench demonstrate AV-GRPO outperforms LTX-2.3 in generation quality, semantic alignment and cross-modal synchronization under LoRA and full fine-tuning. Ablations confirm our designs. Code and data: https://github.com/zhiyuxu03/AV-GRPO

9. AnomaSense: Anomaly-based Sensor Activation for Fine-Grained Human Activity Recognition

Authors: Xue Wang, Yang Zhang

Categories: cs.HC, cs.SD

Audio carries rich cues about human activities, and microphones are already built into most wearable devices. However, microphones also capture speech, and this privacy risk limits their use in Human Activity Recognition (HAR). We present AnomaSense, a sensor activation approach for wrist wearables that keeps the microphone off by default and turns it on for at most one second when an unsupervised anomaly detector flags an IMU segment that is likely to produce sound. The captured audio is further masked before it reaches the recognition model. We study 20 activities from 15 participants, organized into five groups in which activities share similar wrist motion but differ in the object or material involved. With IMU data alone, our recognition model reaches 78.98% accuracy in leave-one-participant-out validation. With the short, masked audio windows added, accuracy reaches 96.89% with no masking and stays above 86% when 90% of each one-second audio window is removed. On the same data, the anomaly detector triggers the microphone with 86.46% precision and 74.28% recall relative to sound events. We also report a small preliminary check of automatic speech recognition on masked speech, which shows that contiguous masking degrades recognition far more than point-wise masking at the same masking ratio. Our evaluation is a controlled, offline feasibility study. We describe the threat model, what the approach does and does not protect, and the steps needed before deployment.

10. To Trust or Not to Trust: Retrieval-Augmented Fact Checking in Speech

Authors: Debajyoti Mazumder, Mamta, Abhirama Subramanyam Penamakuri

Categories: cs.LG, cs.AI, cs.CL, cs.SD

Online misinformation increasingly appears in spoken formats such as news clips, podcasts, interviews, political speeches, and social media videos, creating a need for fact-checking systems that can verify claims directly from speech. We introduce VeriSpeak, a probe benchmark for studying speech-based fact verification in Large Audio Language Models (LALMs). VeriSpeak contains 3,879 spoken claims spanning temporal, geographical, and relational facts, with balanced true and false labels. The benchmark is designed to examine whether factual verification ability transfers from text to speech, and whether retrieval-augmented LALMs can use textual evidence to correctly support or refute spoken claims. Our experiments reveal a consistent text-speech modality gap: LALMs that verify written claims reliably often fail on the same claims when spoken. Moreover, retrieval alone provides limited gains because models frequently conflate retrieved evidence with the spoken claim. In contrast, retrieval combined with explicit reasoning improves claim-evidence comparison, with a thinking-tuned LALM reaching 86.1% accuracy. VeriSpeak highlights that effective speech misinformation detection requires not only speech understanding, but also grounded reasoning over retrieved evidence. The dataset is publicly available via Hugging Face at https://huggingface.co/datasets/abhiram4572/VeriSpeak.

11. Cluster Assignments in Soft Targets Shape Speech Representations: Evidence from S-JEPA

Authors: Wenxuan He, Yunpeng Li, Zewei Li, Yongke Yang, Yuze Li et al.

Categories: cs.LG, cs.SD

Cluster-based prediction is widely used in self-supervised speech learning. A soft target preserves a distribution over clusters rather than a single label. This distribution specifies both the probability values and which clusters receive them. Comparisons between soft targets and hard labels do not separate the contributions of these two aspects to the learned representation. We study this in S-JEPA, a recent high-performing self-supervised speech model trained with soft Gaussian mixture model (GMM) targets. We compare its original targets with counterfactual targets that preserve the most likely cluster and all probability values but change which remaining clusters receive the other probabilities. Across three training seeds, the original soft distribution is recovered more accurately from Encoders trained with the original than counterfactual targets. Because this could reflect target matching alone, we also test low-level acoustic and phonetic information. Both are more accessible from Encoders trained with the original targets. This suggests that cluster assignments affect acoustic and phonetic properties of the learned representation, not just recovery of the training target.

12. ROAM-ASD: Robust Open-World Active Speaker Detection with Flexible Multimodal Fusion

Authors: Pu Wang, Hugo Van hamme

Categories: cs.MM, cs.CV, cs.SD, eess.AS, eess.IV

Active speaker detection (ASD) requires reliable association between visible faces and acoustic speech, yet existing systems often degrade under challenging domains or incomplete observations. We introduce ROAM-ASD, a robust audiovisual framework that jointly models audio, full-face, and fine-grained mouth representations. A unified joint self-attention mechanism processes all input streams together with modality-agnostic query tokens, enabling direct interaction among available modality inputs. Modality dropout further improves robustness when input streams are unavailable. ROAM-ASD achieves state-of-the-art performance across five ASD benchmarks: 98.8% mAP on WASD, 87.9% on UniTalk, 96.5% on AVA, 99.3% on ASW, and 98.2% on Talkies, improving over previous best systems by 5.1, 4.7, 0.9, 1.0, and 2.1 mAP points, respectively. ROAM-ASD also substantially improves zero-shot cross-dataset generalization and remains robust to missing observations.

13. AdaptDuplex: from static to adaptive full-duplex spoken dialogue

Authors: Zhiyang Zhou, Yingxin Shang, Zhou Wang, Hongwei Cai, Weixu Wang et al.

Categories: cs.SD

Full-duplex spoken dialogue requires simultaneous listening and speaking at sub-second latency, under conversational timing and cognitive demands that change moment to moment. Yet current models mostly impose static operating points, lacking a systematic mechanism for adaptive decisions. We present AdaptDuplex, which upgrades Qwen3-Omni with such a mechanism, co-designed across three layers. A compact token-level protocol represents every window as a canonical sequence, trains dual-stream alignment through a bounded text lead over speech, and exposes every behavioral decision as an explicit token for training-free runtime control via logits bias. Adaptive mechanisms dynamically predict among discrete window durations and augment direct response as needed with non-blocking cognitive consolidation and multi-flight external reasoning. A progressive pipeline introduces these behaviors through a three-stage Thinker curriculum, then Talker-only and joint SFT, with GRPO as a further increment. On Full-Duplex-Bench v1 and v1.5, AdaptDuplex outperforms DuplexOmni and MiniCPM-o 4.5 on the majority of comparable turn-taking, overlap-behavior, and timing metrics, with gains in both interaction decisions and response timing. On the human-recorded HumDial-FDBench, it attains the highest Final score (72.9) of the compared duplex models.

14. EditVoice: Variable-Length Non-Autoregressive Zero-Shot TTS and Speech Editing with Edit Flows

Authors: Hongyao Deng, Wenhao Guan, Xuetao Lin, Peijie Chen, Weijie Wu et al.

Categories: cs.SD

Recent non-autoregressive (NAR) zero-shot text-to-speech (TTS) models generate in parallel but typically require the target sequence length to be specified before generation. We introduce EditVoice, to our knowledge the first variable-length NAR zero-shot TTS model, which uses Edit Flows to jointly update speech content and sequence length through insertions, deletions, and substitutions. EditVoice adopts speech-infilling training, which unifies zero-shot TTS and text-based speech editing and allows both prefix and suffix speech prompt placements at inference. We introduce Complementary Prompt Sampling (CPS) to leverage the complementary Edit Flow predictions induced by the two prompt placements. We further find that EditVoice can edit source and model-generated speech beyond its training sources. We use this generalization for end-to-end editing and training-free post-generation refinement. With the Edit Flow model trained on 10K h of GigaSpeech, EditVoice demonstrates competitive zero-shot TTS performance on Seed-TTS Eval EN and LibriSpeech-PC and speech editing performance on RealEdit.

15. Joint Analysis of Latent Dimensionality and Frame Rate in Continuous Audio Encoders

Authors: Kyudan Jung, Sehyun Lee, Son-ha Jo, Jaegul Choo, Sanghyuk Shoi

Categories: cs.SD

Continuous audio encoders compress audio along feature and time axes through latent width and frame rate, but their joint effect on downstream performance remains unclear. We train sixteen encoders spanning four widths and four frame rates, with downstream adapters and probes, using matched training protocols. Despite generally improved reconstruction at larger widths, automatic speech recognition (ASR) and spoken question answering (SQA) favor moderate widths at higher rates, with the best observed widths shifting toward larger values under stronger temporal compression. Frozen-model PCA interventions reveal distinct reconstruction and recognition sensitivities: removing the trailing half of the components substantially degrades ASR in high-rate 512-dimensional encoders with comparatively small reconstruction penalties, whereas 1024-dimensional encoders largely preserve both. Yet the projected 1024-dimensional model underperforms unmodified narrower models on ASR at 12.5Hz. These findings identify a width–rate interaction in downstream utility and suggest that how representations are organized during training matters beyond reconstruction fidelity and compressibility.

16. MIDIBack: Harmony-Aware Singing Pitch Correction via Joint Vocal-Accompaniment Symbolic Modeling

Authors: Joaquim Cavalcante, Yicheng Gu, Adriel Trajano, Yuri Malheiros, Thais Gaudencio

Categories: cs.SD

Automatic pitch correction (APC) requires distinguishing the unintended intonation errors from expressive pitch variation. Existing systems either lack explicit harmonic modeling, as vocal-only methods do, or do not directly use the note-level polyphonic context. Therefore, we propose MIDIBack, a note-level APC framework that jointly models the vocal and accompaniment events in a shared OctupleMIDI sequence. We evaluate MIDIBack under 6 note corruption regimes, including global outshift, learned note-dependent detuning, uniform perturbations, and their combinations. The resulting model achieves 78.6% overall raw pitch accuracy (RPA), and 81.5% under combined global outshift and learned detuning. Removing the accompaniment conditioning reduces RPA from 81.5% to 35.8% in outshift, showing the effectiveness of accompaniment context. Case studies on accompaniment modulation further illustrate that vocal note predictions

17. No Time to Collapse: Unlocking Robustness and Multiplexed Capacity in Frozen Audio Watermarkers

Authors: Xuanye Wang, Linxi Li, Yechen Wang, Liwei Jin, Qianwei Guo et al.

Categories: cs.SD

Modern neural audio watermarking systems typically embed a message repeatedly across time and then collapse the resulting temporal evidence into a single payload using averaging, voting, or another fixed aggregation rule. We argue that this temporal collapse limits both robustness and the recovery of multiple payloads, and that the limitation can be addressed without retraining the underlying watermarker. We freeze a pretrained watermarker’s encoder and detector and train only a low-latency Conformer-based decoder. The decoder consumes the detector’s temporal soft outputs, which a system-specific adapter pools into a sequence of window-level representations, and predicts the embedded message. On three frozen watermarkers (AURA, AudioSeal, and WavMark), the learned decoder improves recovery of attacked messages and yields higher detection AUROC point estimates on all three. Under controlled full- and partial-coverage multiplexing, it improves joint-exact recovery of two alternating payload words by 9.7-48.0, 6.9-17.3, and 8.2-14.2 percentage points, respectively, under one to three chained attacks on feasible clips.

18. Off-manifold robustness in synthesizer inversion with joint distribution flow matching

Authors: Ben Hayes

Categories: cs.SD

Recent work on synthesizer inversion shows that generative models outperform deterministic approaches by explicitly modeling the ambiguity in mapping audio to parameters. Training such models, however, requires audio-parameter pairs, which are typically obtained by rendering sampled or preset parameters through the synthesizer itself. This creates a train-test mismatch that can degrade performance on off-manifold real-world recordings, for which ground-truth parameter annotations do not exist. To circumvent this obstacle, we propose to model the joint distribution of audio and parameters with a multi-modal continuous normalizing flow using independent noise schedules for each modality. This formulation allows us to train joint and conditional densities with paired synthesizer data, while unpaired real recordings can train the audio marginal alone, exposing the model to off-manifold signals without requiring parameter labels. Further, because the model learns to map from audio to parameters at all noise levels, we find that partially noising the audio reference at inference improves real-audio reconstruction, consistent with reducing sensitivity to distribution-specific detail while preserving coarse structure. Evaluating on Surge XT and Dexed, we find that modelling the joint distribution substantially improves both inversion of real-world and in-domain audio.

19. On a Separate Note: Robust Score-Informed Note Separation with a Two-Stream TFC-TDF U-Net and Adaptive Set Ownership

Authors: Benjamin Shiue-Hal Chou, Purvish Jajal, Nicholas John Eliopoulos, James C. Davis, George K. Thiruvathukal et al.

Categories: cs.SD

Score-informed note separation seeks to extract the performed waveform of all individual notes, often from a polyphonic recording. Existing deep learning systems generally only target instrument-level stems. We present, to our knowledge, the first deep learning approach to score-informed note separation, NoteSep. NoteSep extracts the queried notes by applying an extraction stage model, NoteGrab, once per note. Conditioned on pitch, onset, and offset, NoteGrab separates harmonic and percussive components in two U-Nets linked by bidirectional cross-attention; selective harmonic gating suppresses lower-octave interference while preserving percussive attacks. Finally, a joint separation stage applies Adaptive Set Ownership (ASO) to compare concurrent NoteGrab estimates and reallocate mixture energy. We curate SCNS-Train (25,729 mixtures and 743,920 targets) for training and SCNS-Eval (16 instruments, disjoint scores and libraries) for evaluation. On SCNS-Eval, NoteSep reaches a median SI-SDR of 7.39~dB, compared with 2.49~dB for our strongest baseline. See the demo page at https://benschou.com/notesep.

20. ReaFlow-TTS: Realization-Conditioned Flow Matching for High-Quality and Controllable Speech Synthesis

Authors: Junyi Zhao, Yihao Qin, Changsheng Ma

Categories: cs.SD

In flow-matching text-to-speech (TTS), different speech realizations can induce different target velocities under the same generation conditions. A deterministic velocity field trained with squared error predicts their conditional mean, thereby marginalizing realization-dependent variation. Meanwhile, modeling such variation does not inherently provide a semantically interpretable interface for attribute manipulation. We propose ReaFlow-TTS, a realization-conditioned flow-matching framework that introduces an utterance-level stochastic realization latent and uses it to condition velocity prediction throughout the generation trajectory. We further impose valence-arousal-dominance (VAD) semantics on the realization space, enabling direct and graded attribute manipulation without target speech at inference. Experiments demonstrate improved synthesis quality over a matched full-mask baseline and reproducible latent-induced pitch, energy, and timing tendencies across initial-noise samples, providing behavioral evidence that the latent is used as a reusable realization condition. Subjective evaluation further demonstrates graded VAD manipulation across generation contexts with only modest changes in naturalness.

21. Relative Mismatch: Local-Reference Calibration of Feature-Space Flows for Anomalous Sound Detection

Authors: Anbai Jiang, Xinhu Zheng, Lvxin Xu, Shuwei Zhang, Wenrui Liang et al.

Categories: cs.SD

Anomalous sound detection (ASD) has long been dominated by k-nearest-neighbor (KNN) based detectors, which essentially perform implicit likelihood estimation over normal samples. In this work, we investigate whether generative models can better serve this role. We propose Relative Mismatch, a generative ASD backend powered by flow matching, which learns a velocity field that transports Gaussian noise to a representative feature space of normality. During inference, it measures the mismatch between the oracle and predicted path velocities and aggregates them through a two-level design. To mitigate the inherent mismatch offsets incurred by domain shift, each query is further calibrated with the mismatch of its local normal reference, thereby exposing only its deviation beyond normality. Extensive experiments on DCASE 2020–2025 demonstrate that Relative Mismatch outperforms state-of-the-art backends with the highest score of 71.01, along with strong robustness and training stability. Furthermore, we show that curating a compact and discriminative feature space is the key to unleash the power of generative models for ASD.

22. STAM-ASR: Speaker-Temporal Anchoring with Memory for Multi-Speaker ASR

Authors: Victor Tolulope Olufemi, Syeda Faiza Ahmed Sara, Shammur Absar Chowdhury

Categories: cs.SD

Natural conversations make both speech recognition and speaker attribution challenging for ASR, as speakers take turns, overlap, and reappear over time. We propose STAM-ASR, Speaker-Temporal Anchoring with Memory, a lightweight framework that extends an already pretrained AudioLLM for multi-speaker ASR. Without relying on an external diarization system, STAM-ASR learns speaker activity and speaker-aware representations directly from intermediate AudioLLM features. Hence providing explicit who and when cues to modulate the AudioLLM’s semantic representation without explicit speech separation. STAM-ASR further maintains fixed-size speaker and conversational memories to carry complementary context across turns. We evaluate STAM-ASR on AMI, ICSI, LibriCSS, and NOTSOFAR-1 across close-talk, far-field, overlapping, and cross-domain conditions. Our reported results shows that speaker-temporal conditioning and memory provide complementary benefits, while the gap between reference and predicted speaker activity identifies robust speaker tracking as a key remaining challenge.

23. Speech Block Influence: Component-Specific Layer Scoring for Pruning Speech LLMs

Authors: Siyu Yao, Du Q. Huynh, Lian Xu, Mark Reynolds

Categories: cs.SD

Speech LLMs are costly to deploy in resource-constrained settings. Layer pruning can cut this cost, but existing scoring metrics transfer poorly to speech LLMs: they assume a decoder-only architecture with homogeneous token sequences, whereas speech LLMs add encoder and adapter components and process multimodal sequences. We propose Speech Block Influence (SBI), the first layer-importance scoring framework designed for speech LLM pruning that consists of two component-specific scores: SBI-Enc measures the effect of encoder-layer removal at the adapter’s output to better reflect downstream impact; SBI-Dec measures layer-wise input-output similarity over text-token positions only to avoid audio-token dominance. Across three speech LLMs, SBI improves pruning robustness, with stronger encoder performance at higher pruning rates and more reliable decoder layer selection by scoring text tokens rather than the audio-dominated full sequence. We further find that text-only calibration yields decoder rankings highly correlated with those from speech-text calibration, suggesting a cheaper alternative to measure decoder layer importance.

24. TEMA: Evidence-Grounded Temporal Question Answering in Multi-Turn Multi-Audio Dialogs

Authors: Kaidi Yang, Hualei Wang, Zhaohui Wang, Chenxuan Wang, Hong Liu et al.

Categories: cs.SD

Multi-turn, multi-audio temporal question answering requires models to track target events across follow-up questions, recording switches, and historical references, recovering complete instances and their boundaries for temporal calculation and comparison. We propose TEMA, which connects event perception with evidence-based answering through Route, specifying the audio scope, and Span, describing all relevant intervals as conditional audio captions. We construct TEMA-Dialog with 40,704 dialogs and per-turn evidence and answer supervision, and TEMA-Bench for joint evaluation of evidence and final answers. Training combines temporal grounding initialization, full-dialog supervised fine-tuning, and completeness-first Span-only GRPO. Experiments on Qwen2.5-Omni and AF-Next show improved temporal question answering, particularly event localization and cross-audio comparison. Reinforcement learning applied solely to evidence further improves interval recovery and answer accuracy.

25. TS-OPD: Reconciling ASR and QA in Speech Language Models via Task-Specific On-Policy Distillation

Authors: Yujie Guo, Hongjie Chen, Jian Kang, Jie Li, Yongxiang Li et al.

Categories: cs.SD

Speech Language Models (SLMs) inherit strong instruction-following capabilities from pretrained language models, yet ASR specialization can substantially degrade them. To address this ASR–QA trade-off, we propose Task-Specific On-Policy Distillation (TS-OPD), which leverages models before and after ASR specialization as complementary QA and ASR teachers. The student generates separate task-conditioned trajectories for ASR and QA, each supervised only by its corresponding teacher, thereby reducing direct competition between the two supervision signals. Experiments on basic ASR, contextual ASR, and QA demonstrate that TS-OPD improves recognition while preserving QA capability. Moreover, TS-OPD remains robust across different balancing coefficients and continues to benefit from increased distillation data.

26. Broadening Uncertainty Estimation for Audio Question Answering Across Methods, Formats, and Inputs

Authors: Aaron Isidore Grace, Weiran Wang

Categories: cs.SD, cs.AI

Audio-language models can produce confident answers unsupported by the audio, motivating uncertainty estimates that identify unreliable responses. We compare probability-based, sampling-based, self-verification, evidential, and contrastive measures across four open-weight models and five audio QA benchmarks. In multiple-choice evaluation, first-token measures are strongest overall, with top-1 probability achieving a mean AUROC of .740, compared with .708 for ten-sample discrete semantic entropy, while requiring no additional model calls. Across four benchmarks, shifting from multiple-choice to open-ended evaluation lowers mean accuracy from 57.6% to 36.6%, yet uncertainty remains predictive of errors: semantic entropy, maximum token entropy, and semantic agreement achieve mean AUROCs of .697, .694, and .693, respectively. To test whether uncertainty reflects the evidence available to answer the question, we perform input ablations that remove either the audio or the question. Across top-1 confidence, entropy, and sampling-based measures, removing audio reduces error-detection AUROC by .101 on average, compared with .010 when removing the question. Together, these results establish efficient uncertainty baselines and show that uncertainty in audio-language models depends substantially more on available audio evidence than on question text.

27. SHINE: Sequential Hierarchical Integration Network for EEG and MEG

Authors: Xiran Xu, Yujie Yan, Songyi Li, Linze Zheng, Zifeng Zhang et al.

Categories: cs.SD, cs.AI

How natural speech is represented in the brain constitutes a major challenge for cognitive neuroscience. Reconstructing the speech envelope and Mel spectrogram from EEG and MEG provides a time-resolved way to study its temporal and spectral structure. Speech-related neural activity spans sensors and temporal scales; extracting these representations while adapting the use of context to each acoustic target is a central problem in speech reconstruction. We propose SHINE, a Sequential Hierarchical Integration Network for EEG and MEG. A residual sensor adapter unifies input dimensions, intermediate dilated-block states retain temporal depth, and a target- and time-dependent gate fuses local hierarchical and attention-enhanced context predictions. Across two EEG and two MEG datasets, SHINE has the highest mean envelope and mean-Mel Pearson correlations among nine local baseline implementations on all eight dataset-metric combinations. SHINE also placed second in the speech-detection Extended Track of the NeurIPS 2025 PNPL Competition. Code will be released at https://github.com/xuxiran/SHINE.

28. Spot, Separate, and Enhance: Fully Generative Approach for Audio Mixing

Authors: Ilpo Viertola, Giulio Cengarle, Gouthaman KV, Daniel Arteaga, Lie Lu

Categories: cs.SD, cs.AI

We introduce Spot, Separate, and Enhance (SSE), the first multimodal, user-guided generative model for audio remixing and enhancement. SSE enhances video content by rebalancing the audio, removing unwanted audio sources, and reducing reverberation, guided by both video and textual descriptions. To support its training and evaluation, we propose DegradedMix, a new dataset built on the audio remixing benchmark MuddyMix. We also adopt evaluation metrics from generative modeling, which better capture the creative nature of remixing than standard reconstruction-based metrics. SSE outperforms existing baselines in both controllability and remixing quality, as shown by extensive experiments. Project page: https://sse-ai.notion.site

29. Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning

Authors: Yoomee Cho, Jisun Lee

Categories: cs.SD, cs.CL, eess.AS

In cross-lingual zero-shot text-to-speech, the accent of the reference leaks into the target speech. We propose accent analogy guidance (AAG), a training-free sampler term that subtracts an accent direction estimated from the model’s own predictions for one synthetic voice rendered in both languages, so the voice cancels and only the accent remains. By a blind LLM accent judge on real dubbing data, reweighting classifier-free guidance between reference and text, and its variants, stay near one identity-accent trade-off curve; we score a method by its speaker similarity above that curve at equal accent ($Δ$SIM). Across four open TTS models AAG lies above the curve: on OmniVoice $Δ$SIM is +0.11 to +0.27 on three test sets (accent 3.51 to 4.28 on a 1-5 scale at speaker similarity 0.29, where reweighting keeps 0.02); MaskGCT and CosyVoice 2 also lie above their curves, and on F5-TTS it is more native than any reweighting setting. An LLM-free language-ID measure and a twelve-listener panel agree. A premise test and the reach of a model’s own curve indicate in advance whether and roughly how much AAG can gain, predicting the one model where it gains nothing (X-Voice).

30. AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks

Authors: Yu-Ling Liao, Tzu-Chin Chiu, Zong-You Chen, Chi-Lei Tsai, Shao-Yuan Lo

Categories: cs.SD, cs.CR

Large audio-language models (LALMs) expand language models to process and interpret audio, but also expose them to heterogeneous audio jailbreaks. We ask whether successful jailbreaks reflect failures to recognize harmful intent or failures occurring after such recognition. Layer-wise probing reveals the latter: risk-related information remains decodable from intermediate representations, yet the internal risk signal fails to translate into refusal in later-layer processing. We identify this discrepancy as the risk-to-refusal gap. Building on this finding, we propose AEGIS, a detect-then-intervene defense whose mid-layer risk gate selectively activates downstream safety adapters. Across six LALMs and three heterogeneous audio jailbreak benchmarks, AEGIS reduces the average unsafe rate from 17.9% to 0.4%, while causing only a marginal increase in over-refusal on benign inputs. These results establish selective internal intervention as an effective path toward more robust refusal in LALMs. The code is available at https://github.com/azzzzliao/aegis-audio-defense.

31. The Vulnerability of Neural Audio Watermarks under Speech Enhancement

Authors: Xincong Zhong, Shengyao Wang, Lingfeng Yao, Yihang Bao, Jinze Yu et al.

Categories: cs.SD, cs.CR

Neural audio watermarks are increasingly deployed in commercial speech generation systems to make AI-generated speech traceable, yet their robustness has been studied mainly under conventional signal distortions. Since a watermark can be regarded as imperceptible noise added to the speech signal, a natural question is whether speech enhancement (SE), as a denoising model, can remove it. In this paper, we cascade Gaussian noise with SE models as a black-box watermark removal attack, covering both discriminative and generative SE paradigms, against six neural watermarks: AudioSeal, WavMark, SilentCipher, Timbre, Perth, and AlignMark. Experimental results show that the proposed attack significantly outperforms existing neural re-synthesis methods in watermark removal. In particular, we find that generative SE, which reconstructs the harmonic regions of speech while denoising, is highly destructive to watermarks. These findings show that SE poses a serious threat to current audio watermarking methods, and we call for SE-aware robustness evaluation in watermark design.

32. Exploring a Single Autoregressive LLM for Unified Target Speech Extraction across Synchronous and Asynchronous Cues

Authors: Wenxuan Wu, Shuhan Zhang, Shuai Wang, Haizhou Li

Categories: cs.SD, cs.MM, eess.AS

Target speech extraction (TSE) typically trains a separate extractor per cue, and visual-cue systems often need corruption-matched training to remain robust under visual frame corruption. We show that one autoregressive LLM backbone, TSE-Omni, can serve both temporally synchronous cues (lip movements, co-speech gestures) and asynchronous cues (enrollment audio, text). TSE-Omni is driven by next-token prediction: each step predicts target speech semantic tokens from its own past outputs, which we term self-enrollment, forming a continuous target-speech context initialized by the enrollment cue (asynchronous audio or text, or a short visual prefix). This enables audio-visual compensation: the model uses synchronized visuals when intact and its token history when visual frames are missing. Under clean visuals, TSE-Omni matches strong discriminative and generative baselines (SpeechBERTScore 0.81 on VoxCeleb2 and 0.89 on LRS3 zero-shot) with higher DNSMOS. On the same VoxCeleb2 test set, after a 2 s clean visual start, removing the remaining visual frames leaves SpeechBERTScore at 0.81. It remains usable under sparse overlap and multi-speaker interference, and supports streaming inference. Project page: https://alexwxwu.github.io/tseomni-main/.

33. Retain-Free Machine Unlearning for Speech Emotion Recognition

Authors: Zhao Ren, Rathi Adarshi Rammohan, Kevin Scheck, Thanh Tam Nguyen, Sheng Li et al.

Categories: cs.SD, eess.AS

Speech Emotion Recognition (SER) infers a speaker’s emotional state from speech and is increasingly deployed in human-computer interaction, education, and healthcare. Because speech also carries sensitive personal information, speakers may ask that some of their recordings be deleted, which requires removing the influence of those samples from an already trained SER model. Most machine unlearning methods can meet this request only with access to the remaining training data alongside the samples to be forgotten; this is impractical when the remaining data cannot be redistributed or has itself been deleted, and it adds storage and computation as the data grows. To this end, we propose a retain-free unlearning method that updates a pre-trained SER model using only the forget set. Our key idea is to synthesise adversarial samples from the forget set as a surrogate for the unavailable remaining data, and to constrain each parameter update by its estimated importance so that forgetting does not erase general knowledge. The experiments over several emotional-speech corpora and self-supervised backbones show that our method drives forget-set performance down to near chance while retaining much of the model’s utility on the remaining and unseen-speaker data, narrowing the gap to methods that rely on the remaining set.

34. Self-Distilled Pronunciation and Accent Control for Neural Text-to-Speech

Authors: Shuhei Kato

Categories: cs.SD, eess.AS

Text-to-speech that reads raw text has no lexicon: a rare word is read as guessed, and a native Japanese listener accepts a word only if its reading and pitch accent are both right. A known remedy installs a reading-and-accent channel into a released model, but it needs many recordings. This paper removes the recordings: the frozen backbone reads a sentence containing a common word it already says correctly, and that output serves as the teacher for the same sentence with the word replaced by an annotated reading with its pitch accent. Screened raters judged the tag right on 0.80 to 0.93 of unseen difficult words on four backbones spanning autoregressive, diffusion, and encoder-decoder synthesis; plain kana, which cannot express an accent, got 0.38 to 0.60. On words needing no edit, naturalness is non-inferior on one backbone; on the other three, listeners prefer the unedited rendition by 0.19 to 0.26.

35. ARIS: Low-Resource Glass-Box Neural Source-Filter Synthesis for Phonetic Stimulus Manipulation

Authors: Yiran Ding, Wenwei Xu

Categories: eess.AS

Phoneticians often need to construct stimuli in which specific acoustic cues are precisely manipulated while preserving decent speech quality. Classical synthesis and modern neural methods sit along a trade-off between precise parametric control and high fidelity, and neural synthesis typically demands more data than phoneticians can easily obtain. We present ARIS (Analytic Resonant Interpretable Synthesis), a neural source-filter model that pairs neural parameter estimation with deterministic DSP synthesis. Every control is a coefficient of the synthesizer, so F0, formants and the glottal source can be edited directly. On five small single-speaker corpora in three languages, ARIS resynthesizes speech with quality comparable to WORLD and edits single parameters more accurately than Praat KlattGrid, with negligible crosstalk between cues. Compared with HiFi-Glot, pre-trained on a large corpus and fine-tuned on the same data, ARIS scores slightly lower on predicted naturalness but reproduces the recordings more faithfully and manipulates them more precisely. Audio samples: https://n1r.github.io/ARIS_nsf/.

36. COSED: Setting the Bar for Open-Vocabulary Sound Event Detection

Authors: Florian Schmid, Sanjeel Parekh, Chi Ian Tang, Juan Azcarreta, Yijun Qian et al.

Categories: eess.AS

Open-vocabulary Sound Event Detection detects and temporally localizes acoustic events described by arbitrary text queries. Progress in this emerging field is hard to assess: recent methods report on disjoint task subsets under incompatible protocols without a benchmark spanning the acoustic domains and query types the task presents. We establish a comprehensive benchmark by assembling six temporally-annotated tasks: four with fixed class vocabularies over domestic, urban and mixed indoor/outdoor scenes, plus two free-text grounding tasks. We evaluate five recent methods on identical data and metrics under a label-space zero-shot criterion. Our benchmark demonstrates that no prior method is competitive across all six tasks. We then introduce COSED, which surpasses prior work on five out of six tasks while staying on par with the best method on the sixth, with margins of 12-33% on three of them. COSED is the only system in our comparison competitive on every task, and so generalizes across acoustic domains and query types better than prior work. We also provide a leave-one-out ablation study that isolates the sources of the performance benefits: scoping negatives to their corpus of origin (25.8%), combining closed- and open-world supervision (16.8%), and improving temporal processing (16.4%).

37. Configurable-Bandwidth Time-Frequency Modeling for Efficient Full-Band Speech Enhancement Across Sampling Rates

Authors: Ui-Hyeop Shin, Wooseok Kim, Hyung-Min Park

Categories: eess.AS

Speech enhancement systems are often developed for a fixed sampling rate, while time-frequency models become more expensive as the number of frequency bins increases. We propose TF-Refiner, a sampling-frequency-independent model that decouples the deep analysis bandwidth from the full-band input and output. A deep encoder processes the band below a configurable cutoff, while a shallow decoder combines the encoded features with input-dependent high-band queries and predicts local complex filters applied to the original noisy STFT. A single parameter set trained at 16 and 48 kHz is evaluated at various sampling rates. On VoiceBank+DEMAND, the universal model outperforms the rate-specific counterparts in PESQ, STOI, and log-spectral distance across the evaluated rates, including rates unseen in training. Random-cutoff training enables inference-time selection of cost-quality operating points without retraining or changing the output bandwidth. These results support configurable analysis bandwidth as a practical design choice for multi-rate full-band enhancement.

38. DAMSEP: Distance-Aware Monaural Source Separation using Multi-RIR Estimation

Authors: Wen Wen, Qiang Zhou, Yu Xi, Haoyu Li, Bohan Li et al.

Categories: eess.AS

Although room impulse responses (RIRs) encode source-distance cues, conventional monaural source separation focuses on recovering audio content without estimating source-specific RIRs, losing the associated spatial information. To address this limitation, we propose Distance-Aware Monaural Source Separation using Multi-RIR Estimation (DAMSEP), the first end-to-end framework that is jointly trained for source separation and multi-source RIR estimation from a single-microphone mixture. DAMSEP integrates a separation backbone with shared dereverberation and RIR estimation modules to jointly recover clean sources and source-specific complex convolutive transfer functions under source estimation and reverberant reconstruction objectives, enabling relative near/far ordering through the direct-to-reverberant ratios of the corresponding RIRs. For comprehensive evaluation, we introduce HETMIXR, which spans heterogeneous source content and diverse simulated room conditions with source-specific RIRs and geometric distance annotations. Experiments on HETMIXR demonstrate superior performance in source separation, RIR estimation, and distance ordering. Ablation studies reveal the complementary benefits of source supervision and reverberant reconstruction, while additional evaluations show generalization to single-speaker inputs and mixtures generated using measured RIRs from an unseen room. Our code and dataset are available at https://github.com/Wenanzhi/DAMSEP.

39. Deep Filter Estimation from Inter-Frame Correlations for Monaural Speech Dereverberation

Authors: Ui-Hyeop Shin, Jun Hyung Kim, Jangyeon Kim, Wooseok Kim, Hyung-Min Park

Categories: eess.AS

Speech dereverberation with a distant microphone is challenging because reverberation is correlated with the target speech, and models trained on simulated data often generalize poorly to real recordings. We propose IF-CorrNet, a correlation-to-filter architecture for monaural dereverberation. Instead of feeding raw complex STFT coefficients to the network, IF-CorrNet computes inter-frame correlations among neighboring frames at each time-frequency bin and estimates multi-frame deep filters from these features with a dual-path Transformer backbone. This design makes inter-frame dependencies explicit at the network input while retaining a multi-frame filtering output, a pairing motivated by the normal equation of linear multi-frame filtering. On the REVERB Challenge corpus, IF-CorrNet achieves the best CD, LLR, SNRfw, and PESQ among the compared dereverberation baselines on SimData, and the highest SRMR among the compared systems on RealData. The ablation shows higher RealData SRMR with correlation inputs for both filtering and masking, with filtering adding a further gain.

40. Depth through recurrence: Looped transformers for flow-matching TTS

Authors: Jiabao Ai, Peng Han, Yuchen Song, Zhengjun Yue

Categories: eess.AS

We study how to organize Transformer depth through recurrence in flow-matching text-to-speech, varying the amount, order, and place?ment of weight reuse. Seven layouts perform 18 block calls per network evaluation under a common training objective and sam?pler. On Seed-TTS and LibriSpeech-PC, SEQUENCE applies each of nine blocks twice consecutively, retaining competitive intelligibil?ity, speaker similarity, and predicted speech quality at 32 sampling steps with 47.1% fewer parameters than the unshared baseline. Cy?cling six blocks three times further reduces model size but raises 32-step word error rates relative to cycling nine blocks twice. At matched parameter counts and executed depth, reuse order and shar?ing position produce different quality trade-offs. These comparisons depend on sampling budget: Prefix and Suffix have similar 32-step word error rates, but Suffix is worse by 3.44 and 5.97 percentage points at four steps on the two datasets, respectively. Only Middle ranks first or second in mean word error rate at 32 and four steps on both datasets. These results show that the organization of recurrent computation affects synthesis quality, and that reuse layouts should be selected for both the sampling budget and the quality dimensions of interest.

41. Exemplar-Free Analytic Learning for Multi-Label Audio Class-Incremental Learning

Authors: Siyuan Luo, Yang Xiao, Ting Dang

Categories: eess.AS

Audio classification is inherently a multi-label task, as real-world acoustic environments contain multiple simultaneous sound events. When new sound classes emerge, models must incorporate them without forgetting previously learned ones: a challenge known as class-incremental learning. Existing methods rely on storing past data and iterative gradient updates, which struggle under incomplete multi-label supervision because only the newly introduced classes are annotated at each phase, leaving old-class labels unavailable. We investigate exemplar-free analytic continual learning as a principled alternative, in which a linear classifier is updated in closed form without storing historical recordings or performing incremental back-propagation, and previously learned weights remain intact by construction. Building on analytic learning, we further propose ALMA, which addresses incomplete supervision and class imbalance through continuous old-class score estimates and frequency-based sample weighting. Experiments on a 50-class AudioSet-R benchmark across three incremental setups show that the analytic learner substantially outperforms gradient-based methods, and previously learned classes retain nearly unchanged detection performance as new classes are added. This study shows that ALMA is a simple yet effective solution to multi-label audio class-incremental learning.

42. Is Broader Better? A Controlled Study of Multilingual Coverage and Pretraining Objective in Frozen SSL Encoders for Speech Deepfake Detection

Authors: Benjamin Hurt, Oscar O’Donnell

Categories: eess.AS

Frozen self-supervised (SSL) speech encoders are strong, low-cost front ends for audio deepfake detection, and recent comparisons agree that large, multilingual, discriminative encoders generalize best out of domain. These comparisons fail to control for encoder capacity, pretraining objective, and multilingual coverage together, identifying which encoder wins without isolating why. We present a controlled decomposition with a fixed pipeline and trainable capacity. We vary multilingual coverage on four wav2vec2-family encoders, matched to ~315M parameters. We isolate the pretraining objective on two encoders matched on identical data. Coverage does not help monotonically, as out-of-domain error drops sharply at the ~100-language scale (XLS-R) but does not improve further at the 1406-language extreme (MMS). We find that a mid-coverage encoder is strongest on farther out-of-domain sets, matching or surpassing a 577M-parameter model at 315M. Its lead on these far sets, statistically significant under paired bootstrap, and on the official ASVspoof 5 cost metric holds under two backends. Separately, masked-prediction pretraining generalizes better than contrastive on identical data (In-the-Wild EER 26.5% vs. 46.8%). Within this fixed frozen-encoder recipe, we find that broader and larger models are not reliably better.

43. Low-altitude aircraft will reshape noise exposure across global cities

Authors: Tianjing Feng, Jian Kang

Categories: eess.AS

Just as motorisation made road traffic a defining noise source of the twentieth-century city, low-altitude aircraft may reshape urban acoustic exposure in the twenty-first. Yet how this noise interacts with existing sound environments and three-dimensional urban form across global cities remains unclear. We modelled identical low-altitude aircraft operations across ten urban districts spanning all inhabited continents. Horizontal exposure varied markedly across and within cities, depending on road noise conditions and urban morphology, which also strongly influenced overall attenuation. Some semi-enclosed spaces with low noise levels before low-altitude aircraft operations experienced increases above 20 dB(A), creating pronounced local contrasts in urban noise exposure. Vertically, exposure varied with height and acoustic visibility to the flight route, creating vertical exposure inequalities between storeys, façades and buildings at comparable heights. These findings show that low-altitude aircraft can reshape noise exposure across global cities, requiring route assessment to distinguish newly exposed from already exposed areas and to account for three-dimensional exposure.

44. One-Step Voice Conversion by Learning kNN Transport in WavLM Space

Authors: Anton Selitskiy, David Millard

Categories: eess.AS

Voice conversion (VC) systems fall into two families: non-parametric embedding-space methods, which need no trained model but degrade on short target utterances, and spectrogram-based neural architectures, which achieve strong quality via multi-module pipelines with tens of millions of parameters. We propose kNN-FM-VC, a single conditional flow-matching network that learns to approximate the kNN-VC mapping between WavLM embedding distributions of source and target speakers, replacing explicit pointwise kNN matching with a neural regressor trained on kNN-generated pairs. The model is conditioned on the target speaker via cross-attention and FiLM, and trained under three Gaussian conditional paths (Schrödinger bridge, straight line, and constant-variance Gaussian tube), enabling few-step sampling. Unlike Phoneme Hallucinator, which uses an upsampling stage followed by kNN matching, our 13M-parameter model performs conversion with a single learned network and supports one-step inference. On LibriSpeech, the one-step Gaussian Bridge achieves lower WER and higher estimated speech quality than FreeVC and Phoneme Hallucinator. Relative to kNN and kDOT, it substantially reduces WER.

45. Anatomy-aware cross-speaker adaptation of complete vocal-tract acoustic-to-articulatory inversion

Authors: Nhat-Nam Nguyen, Pierre-Andre Vuissoz, Yves Laprie

Categories: eess.AS, cs.AI

Cross-speaker acoustic-to-articulatory inversion requires accounting for anatomical differences between speakers. We propose a geometric adaptation framework that uses anatomical landmarks, primarily on vertebrae and dental structures,to transfer predictions from a fixed inversion model to unseen speakers. An affine transformation followed by thin-plate spline (TPS) deformation maps the predicted contours of 10 vocal-tract structures into each target speaker’s geometry without retraining. Landmarks are identified in one selected /u/ frame per speaker as a common phonetic reference without assuming identical articulatory configurations across speakers, and the resulting mapping is reused across recordings. We train the model on a single-speaker rt-MRI database and evaluate adaptation on eight speakers from a separate multi-speaker rt-MRI database. We compare affine and TPS configurations using 12 or 14 landmarks. Affine12+TPS14 achieves the lowest mean point-to-closest-point error of 3.19mm. These results support the combined value of anatomical landmark information and nonrigid alignment.

46. Qwen-Audio-3.1-Realtime: Towards Reliable Agentic Voice Interaction

Authors: Lujia Bao, Qian Chen, Luyao Cheng, Chong Deng, Yuxiang Kong et al.

Categories: eess.AS, cs.AI, cs.CL, cs.SD

Real-time voice assistants must reason over evolving requests, execute actions, and follow conversational rules. Qwen-Audio-3.1-Realtime brings these requirements together through Think, Act, and Speak and Coordinate. Think combines Core-Cocktail supervised fine-tuning with Multimodality and Multi-Teacher On-Policy Distillation (M$^{2}$-OPD) to transfer language capabilities and develop native audio skills. Act uses self-evolving executable environments and multi-granularity rollouts for Group Relative Policy Optimization (GRPO), teaching the model to use tools, interpret feedback, and complete tasks. Speak and Coordinate aligns whether, when, and how the assistant speaks or acts. We evaluate audio reasoning, multilingual understanding, tool use, conversational behavior, full-duplex interaction, and safety. Compared with Qwen-Audio-3.0-Realtime, 3.1 raises overall task success from 78.4% to 82.0% on our half-duplex speech-to-text adaptation of $τ$-Voice. On speech-to-speech Full-Duplex-Bench v1.5, the response rate to background speech falls from 73.0% to 13.0%. We also present a separate Voice Harness prototype, using Qwen-Audio-3.0-Realtime as its foreground, that extends spoken interaction to persistent tasks through foreground–background coordination and memory.

47. Recovering the Zipfian Distribution in Unsupervised Term Discovery

Authors: Danel Slabbert, Simon Malan, Herman Kamper

Categories: eess.AS, cs.CL

Unsupervised term discovery involves segmenting unlabelled speech into word- or syllable-like units and clustering these into a lexicon of candidate types. True lexicons follow a Zipfian distribution, yet the dominant centre-based clustering approach – K-means – produces a more uniform distribution due to an inductive bias toward spherical clusters. In this paper we revisit graph-based clustering as a bottom-up alternative, where segment embeddings are connected by pairwise similarity and partitioned using the Leiden algorithm. We show that graph clustering substantially outperforms centre-based approaches (K-means, GMM, BIRCH) in both word- and syllable-level lexicon discovery across three languages, producing more Zipf-like distributions. Another bottom-up approach, agglomerative clustering with average linkage, also performs well, although it is computationally less efficient and allows for less control over the resulting distribution. Our work calls into question the dominance of centre-based clustering for term discovery, and promotes graph clustering as an attractive alternative.

48. Personalized Korean Lipreading as Visual Speech Recognition: Transfer, Census and Adaptation on OLKAVS

Authors: Se Un Park, Hakjun Kim, Taehoon Roh, Junyoung Park

Categories: eess.AS, cs.CL, cs.CV

We present a personalized Korean visual speech recognition (VSR) system and quantify, on the nine-camera OLKAVS corpus, the gap between the population-level benchmark score and an individual user’s error. A video-only Conformer initialized from English-trained weights attains 9.95 - 12.19% character error rate (CER) under the corpus protocol against the published 26.64, and 19.00 - 21.52 on unseen wording. Per speaker, CER spans 1.0 to 52.2%, with seen wording lowering CER by 7.0 - 9.0 points and professional delivery and spontaneous speech raising it by 8.5 - 10.5 and 12.7 points. A low-rank adapter with 4.6% of the parameters, trained on 4 to 29 minutes of the user’s frontal video, lowers the CER of twelve high-error speakers by 2.13 to 3.58 points, transfers to every camera without loss, and keeps 85% of the full fine-tuning gain at 12% of its cost to other speakers. Cameras above the mouth plane add about six CER points as a constant offset that training on all views keeps small.

49. Voice Agents under Acoustic Stress: From Signal Degradation to Interaction and Action

Authors: Amir Ivry, Kai-Wei Chang, Lin Zhang, Sharon Gannot, Carlos Busso

Categories: eess.AS, cs.HC

Voice agents must complete users’ tasks despite noise, reverberation, and competing speech. Evaluating agents’ robustness therefore requires following how acoustic conditions affect the conversation and the actions taken on the user’s behalf. This overview examines what existing benchmarks reveal about agents’ ability to complete tasks under acoustic stress and where further task-based evaluation is required. We then introduce TRACE, a practical workflow for designing, running, and interpreting evaluations of acoustic robustness in task-oriented human-agent interactions: the same agent attempts a specified task with an original recording and an acoustically stressed copy, and the resulting conversations are scored for task completion, wrong actions, recovery, and user effort. Finally, we explain how results from these evaluations can guide changes to an agent to prevent wrong actions and improve recovery.

50. Transcript-Supervised Post-Training of Generative Speech Enhancement on Real Recordings via Reinforce Adjoint Matching

Authors: Julius Richter, Christoph Boeddeker, Yoshiki Masuyama, Kohei Saijo, Dominik Klement et al.

Categories: eess.AS, cs.LG

We adapt Reinforce Adjoint Matching (RAM), a reward-based post-training method, to generative speech enhancement (SE). Starting from a pretrained SE model, RAM tilts the model’s conditional distribution toward outputs with higher reward. During training, the current model generates enhanced speech on-policy, evaluates each generated endpoint with a potentially non-differentiable reward, and analytically re-noises the endpoint to construct inputs for a reward-guided regression objective. This enables post-training directly on real recordings using weak supervision, such as text transcripts, without requiring paired clean speech targets or reward gradients. We investigate word error rate (WER)-based post-training and whether recognition performance can be improved without compromising perceptual speech quality. Experiments on real CHiME-4 recordings reduce WER by 5.08 percentage points relative to pretrained FlowSE without reducing any of the reported non-intrusive speech quality metrics. A subjective listening test at the default reward scale finds no statistically significant preference between the post-trained and pretrained models.

51. Beyond Model Size: Redesigning LiSenNet for embedded speech enhancement

Authors: Clément Laroche, Rasmus Kongsgaard Olsson

Categories: eess.AS, cs.LG, cs.SD

Deploying real-time speech enhancement on resource-constrained devices requires meeting strict latency, memory, and energy constraints. Microcontroller NPUs can accelerate neural inference under these constraints, but only through a restricted set of operators in static, integer-quantized graphs. Recent speech-enhancement networks have reduced parameter counts and MACs to levels nominally suitable for microcontrollers, but their operators and execution patterns often remain incompatible with restricted NPUs. We address this gap by redesigning LiSenNet, a 37k parameter sub-band dual-path model, for the STM32N6570-DK Neural-ART accelerator. We replace its recurrent bottleneck with convolutional frequency and temporal mixers, reformulate unsupported operations as static int8-compatible primitives, and use bounded decoder activations to preserve quality after quantization. On VoiceBank-DEMAND, the final NPU-compatible model matches or exceeds the recurrent LiSenNet baseline, reaching PESQ 3.08 versus 3.01 in FP32 and 3.01 versus 2.93 in int8. Deployed on a microcontroller, it processes each 16 ms input hop in 4.83 ms, corresponding to a real-time factor of 0.30. Stateless receptive-field recomputation is an order of magnitude slower at the same frame rate despite higher accelerator utilization. These results show that parameter count and operator compatibility, quantization range, and persistent streaming state must be co-designed to achieve efficient real-time speech enhancement on restricted NPUs.

52. Does per-frame early exit pay? A compute-matched study of dynamic depth for on-device speech enhancement

Authors: Clément Laroche, Riccardo Miccini

Categories: eess.AS, cs.LG, cs.SD

Deep learning-based speech enhancement is increasingly deployed on-device in hearing aids, headsets, and earbuds. Most of these devices, however, can only accelerate static int8 graphs, so a depth-varying network must be implemented as several graphs, orchestrated by a policy. In this paper, we supervise every intermediate depth of one causal model, then we fine-tune its output heads to guarantee that deeper outputs are never worse than shallower ones. Using this training protocol, we can derive a family of static models that are more Pareto-efficient than their equivalently-sized counterparts trained from scratch on the same budget. Specifically, we achieve up to 0.11 higher PESQ for equivalent compute, and match the best PESQ at 30% less compute. We then quantize the models to int8 and measure the latency-quality frontier on an STM32N6 microcontroller. On VoiceBank-DEMAND, the dynamic enhancer lies on the same frontier as the static models, rather than trading quality for dynamic execution. Running the policy on the companion Cortex-M55 takes only 26 $μ$s per frame, while splitting the enhancer into separate NPU graphs adds 2.2% latency overhead. The cost of dynamic execution is therefore small.

53. Same Bit Width, Different Outcomes: Post-Training Quantization of Text-to-Speech Across Architectures

Authors: Se Un Park, Yutae Kim, Junyoung Park

Categories: eess.AS, cs.LG, cs.SD

Post-training quantization (PTQ) reduces the cost of on-device text-to-speech (TTS), but published evaluations cover one system or method. We evaluate PTQ across TTS architectures under one protocol with three core models, weight and activation ablations of eight more, and two held-out models quantized blind. Four-bit per-channel weights reduce UTMOS, a predicted mean opinion score, by 2.8 on Supertonic and 0.07 on Kokoro, and per-tensor scaling can cause severe degradation even at 8 bits. The same bit width yields different outcomes, because the sensitive component is model-specific and not reliably predicted from the model class. A staged ablation procedure identifies it, and per-layer GPTQ can restore it to within 0.1 UTMOS. Real int8 and int4 kernels reproduce the simulated ordering at hardware-dependent cost. On a Mac mini, a 4-bit weight kernel runs Supertonic at 0.60x the fp32 latency while int8 is slower, so each configuration requires validation on the target runtime.

54. Assessing True Generalisability of Audio-Visual Speech Recognisers

Authors: Zhaofeng Lin, Stavros Petridis, Maja Pantic, Naomi Harte

Categories: eess.AS, cs.SD

Current Audio-Visual Speech Recognition (AVSR) models achieve near-perfect performance on the standard LRS3 benchmark, raising concerns of adaptive overfitting. To systematically assess true generalisability, we construct a highly controlled, unseen evaluation set subsampled from the massive MultiVSR dataset. Unlike standard out-of-distribution benchmarks, our subset strictly matches the acoustic, visual, and demographic distributions of the LRS3 test set. Evaluating five state-of-the-art architectures reveals a universal performance collapse, proving that current systems fail to generalise even under strictly aligned conditions. Through a fine-grained attribute analysis across seven factors, we isolate the specific drivers of this degradation. Furthermore, we uncover a profound lexical bias, expose distinct error patterns, and surprisingly reveal that audio-visual performance even lags behind audio-only settings. We release our matched test set for future benchmarking.

55. Pushing the Boundaries of Streaming Multi-Speaker ASR: A Systematic Study of Architectural Trade-offs

Authors: Taejin Park, Ivan Medennikov, Kunal Dhawan, Weiqing Wang, Jagadeesh Balam et al.

Categories: eess.AS, cs.SD

Streaming multi-speaker ASR is a challenging task that must balance accuracy, latency, and efficiency while handling overlapping speech and maintaining coherent long-context modeling over extended conversations in an online fashion. We present a unified framework that categorizes streaming multi-speaker ASR into four architectural strategies based on how diarization and ASR are integrated. Using a shared pair of open-source streaming ASR and diarization models as a common foundation, we derive four multi-speaker ASR systems that differ in whether they employ multiple model instances, fine-tuning, or both. We evaluate these systems across multi-speaker accuracy, single-speaker accuracy degradation, memory footprint, and training complexity. Through this systematic architectural analysis, we clarify the design space for streaming multi-speaker ASR and provide practical guidance for selecting the most suitable approach under diverse deployment constraints.

56. UNITE-AUDIO: Joint Learning of Continuous Tokenization and Latent Flow Matching for Text-to-Audio Generation

Authors: Runwu Shi, Kai Li, Yujin Wang, Dong Yang, Jiahui Li et al.

Categories: eess.AS, cs.SD

Text-to-audio (TTA) generation aims to synthesize realistic audio that faithfully reflects natural-language descriptions. Most TTA systems adopt a two-stage latent paradigm: an audio tokenizer is optimized for reconstruction and then frozen, after which a generative model is trained in the resulting latent space. However, reconstruction-oriented representations may be suboptimal for generation, motivating joint representation and generative learning. To this end, we introduce Unite-Audio, to our knowledge, is the first to jointly learn continuous audio representations and latent flow matching for TTA. By coupling reconstruction with self-supervised generative prediction, Unite-Audio allows the generative objective to directly shape the latent space rather than treating it as a fixed intermediate representation. We further employ Flow-GRPO post-training to improve text-conditioned generation. Experiments show competitive TTA performance with a compact latent flow model, while ablation studies confirm the benefit of jointly learning the audio representation and generative model. Audio samples are available at https://runwushi.github.io/Unite-Audio.

57. Few-Shot Calibration for Sim-to-Real Single-Channel Speaker Distance Estimation

Authors: Michael Neri, Archontis Politis, Tuomas Virtanen

Categories: eess.AS, cs.SD, eess.SP

Speaker distance estimators are trained almost exclusively on simulated room acoustics, because real recordings annotated with the true talker-to-microphone distance are scarce. We show that models trained this way transfer poorly. On three real corpora we evaluate, simply predicting the average distance of the corpus is more accurate than any learned model. Then, we ask how few labelled real utterances are needed to make a frozen, synthetic-trained estimator useful, and study post-hoc calibration maps that rescale its output without gradients or retraining. An analysis of the achievable error shows that what the calibration is not limited by the absolute accuracy of the estimator, but how well it orders utterances by distance, since a constant bias or a wrong output scale is removed exactly by the calibration itself. Balancing this against the cost of estimating each coefficient from few samples yields a criterion that accounts for which map wins on which corpus and at which annotation budget, together with a shrinkage variant that requires no hard decision. Our findings suggest selecting synthetic checkpoints by linear correlation with true distances rather than by absolute error. Code, datasets, and analysis are available at https://github.com/michaelneri/audio-distance-estimation.

58. A Deep Neural Network for Predicting Continuous Human EEG Across the Auditory Pathway in Response to Sound

Authors: Thomas J Stoll, Ross K Maddox

Categories: eess.AS, eess.SP, q-bio.NC

Computational models of auditory physiology commonly target specific responses or stages of the auditory pathway, limiting their ability to integrate findings across experimental paradigms and neural timescales. We present a foundation model of human auditory electrophysiology: a causal neural network trained to map binaural acoustic waveforms directly to high-sample-rate EEG. The model was trained on approximately 250 hours of EEG data from 92 subjects, with varied electrode montages and stimuli spanning tonebursts, speech, and music. We tested whether the model recovered effects of stimulus rate, frequency, and presentation method on auditory brainstem responses (ABRs); subcortical and cortical temporal response functions (TRFs) to continuous speech; and the click-evoked binaural interaction component (BIC). Predicted ABRs and TRFs reproduced established response morphology and stimulus-dependent effects, with model-grand-average correlations falling within the corresponding subject-level human distributions. The model-predicted BIC metrics closely resembled the values reported in the literature. These findings demonstrate that a single audio-to-EEG model can capture auditory physiology across paradigms and timescales, supporting future in silico experimentation and hearing technology applications.

59. Exact Factorisation and Fast Computation of Invertible Constant-Q Transforms

Authors: Facundo Franchino, Eloi Moliner, Vesa Välimäki

Categories: eess.SP, cs.SD, eess.AS

The constant-Q transform (CQT) represents audio on a logarithmic frequency axis. Its nonstationary Gabor formulation is exactly invertible, but the unequal numbers of time coefficients in its bands complicate GPU computation. An exact factorisation combines spectral selection, conjugation, windowing, and reordering into a fixed map between one packed Fourier transform and the shorter band inverse transforms. The factors give waveform reconstruction, real adjoints for backpropagation, and bounds on arithmetic depth and block width; overlapping slices permit streaming with bounded memory. Tests on two GPU models show that Flash-CQT reduces analysis-synthesis round-trip time by factors of two to eight relative to a baseline computing the same CQT. The proposed implementation also uses over 30% less peak temporary workspace and reaches a negligible reconstruction error, with a signal-to-noise ratio of about 130 dB, in single-precision floating-point arithmetic. These advances make Flash-CQT a practical, computationally efficient front end for spectral analysis and modern audio machine-learning systems.

60. Decoding Imagined Speech: A Strictly Subject-Independent Approach Using EEG

Authors: Frederik Møllskov Trier, Xiaopeng Mao, Sadasivan Puthusserypady

Categories: cs.AI

Imagined speech decoding from electroencephalography (EEG) has gained increasing attention as a potential communication pathway for individuals with severe motor impairments, yet reported performance often relies on evaluation protocols that do not clearly reflect cross-subject generalization. This study presents a transparent baseline investigation of a multi-class imagined speech EEG dataset under a strictly subject-independent evaluation framework. Two preprocessing and feature extraction pipelines were compared: a time-domain statistical feature approach and a frequency-domain spectral bandpower approach, evaluated using subject-wise cross-validation and trial-level majority voting with a random forest classifier. The spectral pipeline achieved a significantly higher mean trial-wise accuracy than the statistical pipeline (49.03 $\pm$ 4.18% vs. 37.97 $\pm$ 3.79%) for coarse-level classification across subjects. Forward feature selection further indicated that a limited subset of frequency bands captured most of the discriminative information. Overall, this work provides a strong basis for future brain-computer interface studies targeting improved cross-subject generalization in EEG-based imagined speech decoding.

61. Adaptive Fisher-Whitened Cross-Covariance for Low-Resource Speech Recognition

Authors: Asmee Mishra, Mengjie Qian, Brechtje Post, Kate Knill

Categories: cs.CL

Adapting multilingual speech foundation models to low-resource languages remains difficult, especially for languages that are poorly represented during pre-training. While parameter-efficient fine-tuning (PEFT) reduces the cost of adapting large models, conventional approaches such as LoRA rely on generic low-rank parameterizations and do not explicitly use downstream task information to define the adaptation subspace. To investigate whether task-informed PEFT can better support low-resource ASR, we apply Fisher-Whitened Cross-Covariance Analysis (FCCA) to Whisper and Qwen3-ASR, and introduce two complementary extensions: Asymmetric-Coupled FCCA (AC-FCCA), which exploits structured cross-layer sharing, and Adaptive-Rank FCCA (AR-FCCA), which reallocates adaptation capacity across projection matrices under a fixed parameter budget. Under controlled multilingual experiments, we evaluate these approaches on languages that are poorly represented or unsupported during pre-training alongside well-represented languages. Standard FCCA is competitive with, and usually outperforms, trainable-parameter-budget-matched LoRA. AR-FCCA provides the most consistent improvement over standard FCCA across both model architectures, with statistically significant gains in several evaluation settings, while retaining the same number of trainable parameters. These results show that task-informed subspace construction can be effective for low-resource speech adaptation, and that adaptive rank allocation provides a robust way to improve parameter efficiency without increasing model capacity.

62. BanglaKontho: Closing the Long-Form Gap in Bangla Text-to-Speech

Authors: Mizbaul Haque Maruf

Categories: cs.CL

Bangla, the seventh most spoken language in the world, remains under-resourced for neural text-to-speech. Public Bangla speech corpora are dominated by short read-prompt utterances collected for speech recognition, leaving long-form prosody and consistent single-speaker narration uncovered. We present BanglaKontho, a single-speaker Bangla TTS corpus of 20 hours derived from professional audiobook recordings: 7,050 segmented utterances with verified transcripts at 24 kHz. We also release a reusable Bangla text normalizer covering Bangladeshi-style digit grouping, currency and date expressions, Danda punctuation and Unicode normalization, together with the full preprocessing pipeline. An MB-iSTFT-VITS baseline trained from scratch reaches 9.5% WER and 4.46 naturalness MOS, against 16.0% and 3.16 for the same architecture retrained on the 12-hour IndicTTS-Bn corpus. The corpus is released openly under CC BY-NC 4.0.

63. BanglaTurn: A Benchmark and Whisper-Based Model for End-of-Turn Detection in Bangla Speech

Authors: Mizbaul Haque Maruf

Categories: cs.CL

This paper presents BanglaTurn, a corpus for end-of-turn detection in Bangla conversational speech, and a model trained on it. The corpus holds 35,374 samples of 3 to 15 s of podcast speech, labelled for turn state by combining speaker diarization with an LLM pass, with every label then checked by a human annotator. The model pairs a Whisper encoder with task-specific classification heads. On a class-balanced test set drawn from a held-out podcast, it reaches 84.33% accuracy (95% CI 80.3 to 88.1) against 69.28% for the Smart-Turn v3 baseline, and lowers the false negative rate from 51.57% to 7.55% at the cost of a higher false positive rate. We report what encoder layer fine-tuning, multi-scale pooling and INT8 quantization each contribute, and latency stays within 165 to 191 ms end to end on CPU.

64. Closing the Quality Gap in Low-Resource Text-to-Speech: LoRA Fine-Tuning of VoxCPM2 for Khmer and Korean

Authors: Phannet Pov, Hyun Woo Park, Voneat Pen, Sovandara Chhoun, Wan-Sup Cho et al.

Categories: cs.CL

Large pretrained text-to-speech (TTS) models sound almost human for well-resourced languages, but much worse for languages that are rare in their training data. We study this quality gap for Khmer and Korean using VoxCPM2, a 2.4B parameter, tokenizer-free TTS model that joins a MiniCPM-4 language-model backbone with a flow-matching diffusion decoder. We build one shared, language-tagged corpus of 25.5 hours after cleaning and adapt VoxCPM2 with a single Low-Rank Adaptation (LoRA) adapter, trained on both languages at once and added to both the language model and the decoder. The adapter is zero-initialized, so training starts exactly at the original zero-shot model. In native-speaker listening tests, the Khmer Mean Opinion Score (MOS) rises from 3.85 to 4.23 with the best adapter, rank 64. This gain is highly significant under a paired Wilcoxon test with p < 0.001, and it is achieved while training only 0.19 to 3.03 percent of the parameters. Two findings stand out. First, the training loss and human ratings disagree on the best rank. The loss is lowest at rank 128, but MOS peaks at rank 64. Second, the same adapter gives no significant gain for Korean, which the base model already covers well, and a high rank even hurts quality. This shows that adaptation helps mainly where the base model is truly weak.

65. DuplexDrama: A Synthesized Dialogue Dataset with Scenarios, Full-Duplex Behaviors, Expressive Speech, and Sound Events

Authors: Qingxiang Guo, Wenke Fan, Shuofeng Zhao, Dawei Yang, Zhiyang Zhou et al.

Categories: cs.CL

We present DuplexDrama, the first synthesized spoken dialogue dataset that simultaneously covers four dimensions: (i) complete persona and scenario settings; (ii) three full-duplex behaviors (interruption, backchannel, incomplete); (iii) expressive speech with persona-aligned emotion labels; and (iv) script-aware sound events. DuplexDrama is built via a 4-stage pipeline; quality validation on both scripts and synthesized audio confirms its quality. We have produced more than 2,000 hours audio data with a 64-voice timbre pool spanning 13 personas and 5 age buckets; 3.8% of all turns carry at least one full-duplex behavior. This data has been validated through internal full-duplex model training. We will release a curated subset of 6,400 bilingual dialogues (800 h, Chinese ~500 h + English ~300 h) to advance full-duplex spoken dialogue model research. Data samples are available at our demo page and LLM-judge evaluation prompts will be released with the dataset.

66. Interactive In-Meeting Speaker Correction with Human Feedback

Authors: Xinlu He, Yiwen Guan, Badrivishal Paurana, Pitipat Kongsomjit, Zilin Dai et al.

Categories: cs.CL

Most automatic speech processing systems operate in ``open loop’’ mode without user feedback about who said what, yet human-in-the-loop workflows can potentially enable higher accuracy. We propose an LLM-assisted in-meeting speaker correction system that lets users fix speaker attribution errors through brief corrective feedback. After performing streaming ASR and diarization, the system presents concise LLM-generated summaries to help users identify important speaker errors, and it incorporates user feedback by updating the speaker-attributed transcript and adding online speaker enrollments. To make this workflow effective despite errors in speech processing, LLM analysis, and user feedback, we developed several mechanisms to identify the intended correction more precisely. Further, we built an LLM-driven user feedback simulation to evaluate the workflow reprodubilty and at scale. Applied to the AMI headset test set, our system substantially reduces the DER from a streaming baseline (Google ASR + ECAPA) by 31.99% and speaker substitution error by 52.68%. Results of a pilot usability study suggest several avenues to improve the user experience.

67. Parts-of-Speech as Emergent Categories in SAE Latent Space

Authors: Alessandro Bondielli, Lucia Passaro, Serena Auriemma, Alessandro Lenci

Categories: cs.CL

Sparse AutoEncoders (SAEs) offer a promising way to inspect language model representations, but it is still unclear what kind of linguistic structure their latents expose. We use part-of-speech (PoS) categories as a controlled test case to study whether morpho-syntactic information is encoded by individual latents or by structured groups of features. We find that PoS distinctions are highly recoverable from SAE activations, but do not align with one-to-one latent / category mappings. This recoverability is not reducible to lexical memorisation, and Open and Closed PoS classes differ substantially. Categories are supported by compact groups of sparse latents, with substantial variation across tags. These groups remain stable on held-out data, while also showing overlap between related categories. Our results show that SAEs localise morpho-syntactic information in a distributed and category-dependent form rather than through atomic grammatical features.

68. YODAS v3: Over 1 Million Hours of High-Bandwidth, Stereophonic, Multilingual Speech

Authors: William Chen, Shinnosuke Takamichi, Sayaka Shiota, Satoru Fukayama, Samuele Cornell et al.

Categories: cs.CL

We present YODAS v3, a weakly-labeled speech corpus containing over 1.1 million hours of 48kHz multi-channel audio in 147 languages, released under a CC BY 3.0 license. YODAS v3 is not only the largest open speech dataset to date, but also the first truly large-scale speech corpus with high-fidelity stereo audio. We first provide the collection methodology for the corpus, where we introduce new techniques for gathering language-balanced speech data. The effectiveness of our approach is shown by the language distribution of the crawled data: 22 languages in YODAS v3 have over 10K hours and 73 languages have over 5K hours of data. We then conduct extensive analyses on the composition of the data, such as the distribution of languages, audio quality, and transcription quality. Finally, we train baseline speech recognition and neural codec models to show the effectiveness of the dataset. Download at https://huggingface.co/datasets/espnet/yodas3.

69. Benchmarking and Domain Adaptation of Automatic Speech Recognition (ASR) for Adolescent Health Communication in Ghanaian Languages

Authors: Stephen E. Moore, Akwasi Asare, Mich-Seth Owusu, Paul Azunre, Joel Budu et al.

Categories: cs.CL, cs.AI

This paper presents an end-to-end study of automatic speech recognition (ASR) for adolescent health communication in three Ghanaian languages (Twi, Dagbani, and Ewe). The work proceeds in three connected stages; First, we benchmark five ASR systems (three language-specific Wav2Vec2 models and two multimodal LLMs, Gemma 3n and Gemma 4) on a general-domain Bible corpus and a Youth Adolescent Sexual and Reproductive Health (ASRH) Domain ASR dataset, using Character and Word Error Rate (CER, WER). Second, guided by the benchmark, we perform supervised domain adaptation: although Gemma 4 was the strongest zero-shot candidate, fine-tuning it proved computationally infeasible, so we pivoted to the compact Qwen3-ASR-0.6B, fine-tuned on a large Ghana Bible corpus (~90k samples) and evaluated strictly on held-out human-collected in-domain audio. Fine-tuning reduced WER on every language, most dramatically for Ewe (WER from 109.3% to 64.8%, a drop of 44.5 pp; CER from 65.1% to 24.9%). Third, we validate the work through KasaHealth, a live voice-first ASRH application deployed in all three languages, complemented by Senti-Check, a technical evaluation harness. KasaHealth was tested by 50 community respondents and achieved a 100% chat-approval rate, a 72% Good-or-Excellent translation rating, and a 92% would-recommend rate, while surfacing the domain gaps that most constrain real-world use. Across all three stages the evidence converges: for these languages the binding constraint is validated in-domain data, not model capability or computation.

70. agentic-ger: terminology recovery in long-form speech using global context

Authors: Yanqiao Zhu, Wupeng Wang, Zhifu Gao, Xiangang Li, Xie Chen

Categories: cs.CL, cs.AI

Recent advances in speech language models have improved automatic speech recognition (ASR) for long-form audio. However, accurately and consistently transcribing domain-specific terminology remains challenging. Motivated by the world knowledge and contextual capability of large language models (LLMs), we propose Agentic-GER, an LLM-based agent for terminology correction in long-form speech. The agent uses global context from the full transcript to identify suspicious terms and resolve ambiguous hypotheses. It selectively re-transcribes the source speech to check candidate corrections, and uses accepted edits to guide subsequent decisions. Experiments with four LLMs and two ASR systems on GigaSpeechBench show consistent terminology improvements in both Chinese and English, with and without thinking. On Chinese speech, Agentic-GER achieves up to a 36.8% relative reduction in biased character error rate (B-CER) over the Whisper baseline.

71. What, When, and How: Audio Description as Constrained Global Optimization

Authors: Igor Sterner, Mirella Lapata, Alex Lascarides, Frank Keller

Categories: cs.CL, cs.CV

Audio Description (AD) makes movies accessible to blind and visually impaired audiences by narrating visual information in gaps between dialogue. Existing automatic AD systems largely treat generation as a local video-to-text problem, assuming that the content to describe and its temporal location are already provided. Realistic AD instead requires coupled decisions about what visual information is narratively important, when it can be spoken without interfering with dialogue, and how it should be formulated to fit within the available time. We formalize AD generation as a constrained optimization problem over these three decisions. Our hybrid system uses large language models to propose and ground visual elements, estimate their salience to the narrative, and generate compressed realizations. A mixed-integer linear program then jointly selects and schedules descriptions across a scene subject to temporal constraints. When evaluated on REFRAMED, a benchmark for realistic AD of movies, our approach makes better decisions than prompted LLMs about what to describe and when to describe it, establishing a new SOTA on narrative QA and temporally grounded metrics. Ablations show that explicit temporal constraints drive gains in placement, while salience estimation controls how much narratively useful content is retained. Improvements are concentrated on temporal and narrative measures rather than n-gram overlap, although a significant gap to professional describers remains.

72. Pose Adaptive Dynamic FiLM Modulation for Visual Speech Recognition

Authors: Matthew Kit Khinn Teng, Haibo Zhang, Takeshi Saitoh

Categories: cs.CV

Head-pose variation introduces substantial appearance transformations in visual speech recognition (VSR), making pose-aware feature modulation desirable. However, performance degradation and unwanted feature interactions may result from using numerous Feature-wise Linear Modulation (FiLM) circuits with fixed modulation intensity. We propose a Pose Adaptive Dynamic FiLM framework with a Dynamic Residual FiLM (DR-FiLM) modulator that predicts input-dependent weights to adaptively control the strength of pose-conditioned modulation. Experiments on LRS2 and LRS3 demonstrate that unweighted multi-pathway modulation substantially degrades phoneme recognition, increasing PER to 20.33% and 29.42%, respectively, compared with 16.20% and 20.96% for the single ResFiLM configuration. In contrast, the proposed DR-FiLM with dynamic Deep-Res weighting reduces PER to 15.74% on LRS2 and 23.91% on LRS3, substantially mitigating the adverse effects of unweighted modulation. The analysis of the learned weights further reveals a consistent tendency to assign greater weight to the deeper FiLM pathway as head-pose variation increases. These results show that merging pose-conditioned FiLM circuits is more efficient when the modulation strength is dynamically controlled.

73. Less is More: Encoder-only Audio-Visual Segmentation

Authors: Ilpo Viertola, Vladimir Iashin, Sophie Tötterström, Esa Rahtu

Categories: cs.CV, cs.AI

Audio-Visual Semantic Segmentation (AVSS) aims to identify, segment, and classify sound-emitting objects in video frames. Previous Transformer-based AVSS approaches largely inherit design principles from image segmentation models. Recent studies show that these image segmentation models contain redundant components that contribute little to the segmentation performance. Following this insight, we propose Encoder-only Audio-Visual Segmentation (EASE). EASE runs at up to 365 FPS, 3x faster than prior State-of-the-Art (SotA) AVS models at comparable accuracy, and trains in under 11 GPU-hours. Furthermore, we achieve SotA AVSS performance across different backbones and input resolutions. Our results demonstrate that AVSS can be both simpler and faster, providing a scalable foundation for future research and real-time applications. Code, model weights, and samples are available at https://ease-avs.notion.site

74. PolyUMI: Accessible Visual-Tactile-Audio Data Collection for Object Inference and Manipulation

Authors: Conor W. Hayes, Rickmer Krohn, Aravind Ramaswami, Anunth Ramaswami, Nils Dengler et al.

Categories: cs.RO

Humans typically rely on vision, touch, hearing, and proprioception to perceive contact and adapt their actions during manipulation. Providing robots with comparable responsiveness therefore requires hardware that can retain and use these complementary sensory signals. Most imitation-learning systems, however, observe demonstrations primarily through vision and proprioception, limiting access to contact information that is difficult to infer visually. We present PolyUMI, an open-source platform for scalable visual–tactile–audio demonstration collection and robot deployment. Its lightweight, wireless handheld gripper records synchronized wrist-camera, optical tactile, contact-audio, and proprioceptive observations without requiring a tethered workstation. The same sensing finger can be transferred to the robot end effector, preserving the sensing geometry between demonstration collection and policy execution. To effectively use these heterogeneous observations, we further introduce VisTA, a token-level multimodal policy that integrates information across sensors and time to predict contact-aware robot actions. Experiments spanning object inference, slip control, and contact-rich manipulation show that touch and audio reveal task-relevant information beyond vision and that VisTA is competitive with or outperforms existing multimodal policies. Together, PolyUMI and VisTA provide an accessible pipeline for collecting multimodal demonstrations and learning policies that perceive physical interaction beyond vision. Project Page: https://polyumi-vista.github.io