Peer Revenue Publish or profit

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Electrical Engineering and Systems Science Audio and Speech Processing

eess.AS Watch Audio and Speech Processing

Thursday 10 September

Audio and Speech Processing

Domain-Incremental Learning for Multi-Channel Replay Speech Detection

Michael Neri

Replay attacks are the most accessible threat to voice-controlled systems, and the acoustic cues that expose them are strongly modulated by the environment in which the attack is mounted. A detector deployed in the field therefore has to absorb new acoustic conditions over time, ideally without revisiting past recordings, since retaining speech indefinitely is both expensive and legally constrained. We frame this as Domain-Incremental Learning (DIL) over acoustic environments and present the first continual learning benchmark for multi-channel replay speech detection, evaluating a state-of-the-art beamformer-based detector over all 24 environment orderings of the ReMASC corpus with five seeds. Sequential fine-tuning forgets severely, raising the error rate on previously learned environments by 18.8 points. Elastic weight consolidation (EWC) halves forgetting but loses plasticity, gradient projection memory (GPM) is statistically indistinguishable from naive fine-tuning, and the proposed task-specific beamformer (TSB) that keeps one spatial front-end per environment significantly improves final and incremental accuracy. We further show that the last environment of the sequence dominates final performance. Code, results, and analysis are available at https://github.com/michaelneri/replay-speech-continual.
Read the full abstract

Audio and Speech Processing

Exploring Second-Order Pattern Recognition in Speaker Recognition

Yanze Xu, Wenwu Wang and Mark D. Plumbley

In traditional pattern recognition tasks, neural networks are trained to recognise human-defined patterns (e.g. audio categories) in model inputs (e.g. audio). Meanwhile, some Explainable AI (XAI) methods explain latent patterns characterising the network's recognition of inputs as human-defined patterns; this work calls these latent patterns second-order patterns and proposes to discover them. Accordingly, we apply a hierarchical clustering algorithm to analyse whether our speaker recognition network's representations learned from known utterances naturally form hierarchical clusters. Each resulting cluster is a second-order pattern that characterises a context in our network's recognition of the known utterances as speaker identities. All discovered second-order patterns are then interpreted using the Hierarchical Cluster-Class Matching (HCCM) method. Moreover, we propose a new task, second-order pattern recognition, to identify which of the discovered second-order patterns characterising the recognition of known utterances also apply to unseen utterances, thereby characterising the recognition of unseen utterances. Accordingly, we design the Hierarchical Cluster Navigation and Assignment (HCNA) method. HCNA recognises a second-order pattern as applying to an unseen utterance when the utterance's network representation lies within the extrapolation space of the cluster regarded as that second-order pattern. Experimental results demonstrate that the extrapolation space introduced in HCNA substantially improves task performance.
Read the full abstract

Audio and Speech Processing

Low-Latency State Space Voice Activity Detection with Robust Onset Time Evaluation

Elad Cohen, Arnon Netzer and Hai Victor Habi

Voice Activity Detection (VAD) systems are commonly evaluated using metrics such as the area under the receiver operating characteristic curve (AUROC), but these metrics do not account for temporal responsiveness. For low-latency applications, however, accurately measuring speech onset delay is essential. This is particularly challenging because onset latency evaluation is affected by noise and systematic misalignment in annotation timestamps. In this work, we introduce a probabilistic framework for evaluating VAD onset time under noisy temporal labels. We model annotated onset times as noisy observations of latent acoustic onsets and estimate the resulting discrepancy distribution from data. We show that this approach provides a more stable and robust estimate of algorithmic latency. In addition, we introduce S4VAD, the first state-space-model-based (SSM-based) VAD architecture. S4VAD supports efficient streaming inference while directly controlling the decay of past acoustic evidence, enabling fast and responsive speech-onset detection. We evaluate VAD onset latency across several low-latency architectures, including CNN, Transformer, and RNN models. Our proposed VAD achieves the lowest latency while maintaining a competitive AUROC.
Read the full abstract

Audio and Speech Processing

Downstream-Task-Aware Unified Source Separation

Yoshiki Mitsui, Ryo Aihara, Tatsuhiko Saito et al. (+5 more)

Task-aware unified source separation (TUSS) enables a single model to handle diverse separation tasks by conditioning on input prompts. However, conventional TUSS does not account for downstream task requirements, such as whether the enhanced speech will be used for human listening or automatic speech recognition (ASR). In this paper, we propose a prompt extension framework for TUSS that incorporates downstream task information into the input prompts and switches the loss function according to the given prompt during training, enabling outputs with different signal characteristics at inference time. Specifically, we introduce an ASR-dedicated prompt paired with a regularized loss function that reduces speech artifacts to improve ASR robustness, while the standard prompt is paired with the conventional SNR loss function. Experiments on the LibriSpeech and JNAS corpora demonstrate that the proposed joint-training scheme enables a single model to improve ASR performance over noisy input across a wide range of SNR conditions by selecting the ASR-dedicated prompt, while maintaining general speech enhancement quality when the standard prompt is used.
Read the full abstract

All authors Yoshiki Mitsui, Ryo Aihara, Tatsuhiko Saito, Yoshiki Masuyama, Christoph Boeddeker, Julius Richter, Gordon Wichern, Jonathan Le Roux

Audio and Speech Processing

Less can be More: What Aspects of Speech Drive End-of-Turn Detection

Rini Sharon, Manickavela A, Kadri Hacioglu et al. (+1 more)

In conversational AI, detecting when a speaker has finished talking is crucial for natural turn taking. While recent work incorporates semantics, the relative contribution of different modalities remains unclear. We present a controlled ablation of acoustic, prosodic, and semantic signals for streaming end of turn detection using a lightweight trimodal classifier. Under identical training conditions, the acoustic prosodic combination achieves the best balance of accuracy and latency, achieving utterance F1 of 0.93 with 7.8% false alarms at 400ms median latency. Adding text increases premature detections without improving performance. Feature space analysis confirms that prosodic features have the strongest class separability, while text representations overlap substantially. These findings suggest that turn-taking is primarily conveyed through intonation and silence patterns rather than semantic completeness, enabling faster and more reliable systems without expensive text inference.
Read the full abstract

All authors Rini Sharon, Manickavela A, Kadri Hacioglu, Andreas Stolcke

Audio and Speech Processing

Diarization Error Decomposition Under Pause Annotation Ambiguity

Shota Horiguchi, Marc Delcroix, Naohiro Tawara et al. (+1 more)

Speaker diarization evaluation is sensitive to ambiguity in pause annotation, which can inflate diarization error rate (DER) or obscure genuine model errors. We show that morphological closing, which has been used for pause-tolerant diarization evaluation, discards segment-level distinctions. Instead, we propose an exact, overlap-aware decomposition of standard DER into a pause-attributable component, consisting of errors compatible with pause filling, and a residual core component that can serve as a proxy for intrinsic diarization errors. The decomposition leaves DER unchanged, while the pause-attributable and core components vary monotonically with the pause threshold and eventually saturate. Experiments spanning synthetic transformations, annotation mismatch, cross-domain evaluation, and tight-boundary diarization show that the decomposition reveals error sources not apparent from standard DER.
Read the full abstract

All authors Shota Horiguchi, Marc Delcroix, Naohiro Tawara, Alexis Plaquet

Wednesday 9 September

Audio and Speech Processing · Cross-listed from cs.SD

ScorePrompts: Natural-Language Exploration of Symbolic Music Scores through Analysis

Emmanouil Karystinaios and Gerhard Widmer

We present ScorePrompts, an interactive system in which users upload a score, receive natural-language descriptions of its musical structure, ask questions about specific passages, and inspect the corresponding analysis results in staff notation. Specialist MIR components first estimate harmony, tonality, cadences, formal boundaries, texture, and note-level roles, organizing their outputs at note, beat, measure, and piece levels. A schema-constrained language model converts these results into descriptions rather than inferring musical structure directly from raw MusicXML. For questions such as "What changes in measures 14-18?", a deterministic router selects the relevant measures and analytical levels and returns a concise response together with the underlying results and caveats. Verovio renders the score and links the returned information to cited measures and note-level attributes. The interface also exposes intermediate tables and disagreements between analytical levels. ScorePrompts is intended for exploratory score analysis and explanation, not score editing. The demo shows how existing analysis models, constrained language generation, Q&A retrieval, and notation-based visualization can provide natural-language access to symbolic music analysis while keeping intermediate results inspectable.
Read the full abstract

Audio and Speech Processing

From Metrics to Natural Dialogue: French Full-Duplex Benchmark for Spoken Dialogue Models

Hamid Soltani and Gilles Boulianne

Full-duplex spoken dialogue models aim to make voice agents more natural by allowing them to listen, speak, pause, and respond during ongoing conversation. However, it is not clear whether full-duplex benchmarks behave the same way when models are evaluated in a different language. To investigate this, we introduce a French full-duplex benchmark (FDB) with two variants, CALLFC-FDB for Canadian French and MEDIA-FDB for European French, and compare them with an English FDB. Built from real spoken resources, these benchmarks evaluate key full-duplex skills, including pause handling, turn-taking, backchannels, and interruptions. Beyond introducing French FDBs, we evaluate human–human conversations with FDB metrics to better understand the values these metrics take in real-world dialogue. Our analysis reveals that most timing-based metrics behave similarly across languages, while content-based evaluation degrades under language mismatch. We also find a trade-off between optimizing benchmark metrics and preserving conversational naturalness.
Read the full abstract

Audio and Speech Processing

Phoneme-Aware Pronunciation Representations for L2-English L1-Background Accent Identification

Yangyang Qu, Massimiliano Todisco and Nicholas Evans

We study speaker-disjoint accent identification for L2 English, where the goal is to predict a speaker's first-language (L1) background from English pronunciation. Most existing systems classify accents using a single utterance-level representation, but such global representations can obscure pronunciation cues that depend on specific English phonemes. We propose a transcript-assisted model that makes phoneme information explicit during accent identification. Instead of representing an utterance only as a global speech embedding, we represent it as a sequence of pronunciation units, each combining acoustic evidence from a spoken segment with the aligned English phoneme for that segment. A frozen speech encoder provides the acoustic features, while the transcript is used only to obtain phoneme-level forced alignments. No word-level or sentence-level text representation is passed to the accent classifier. Under a four-fold speaker-disjoint protocol on L2-ARCTIC, our model achieves 81.41% accuracy and 81.21% macro-F1, the highest mean performance among the evaluated systems. Diagnostic ablations support the importance of phoneme-aligned token construction, while a Whisper-based ablation shows an additional gain from phoneme information.
Read the full abstract

Audio and Speech Processing

Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition

Rishabh Jain, Aristeidis Papadopoulos, Zhaofeng Lin et al. (+1 more)

Current audio-visual speech recognition (AVSR) benchmarks, like LRS3, rely heavily on clean, scripted and rehearsed speech. They fail to reflect the complexity of natural conversation, which involves overlapping speech, spontaneous turn-taking, unscripted vocabulary and variable acoustic conditions. To shift the field toward realistic dialogue, we introduce Candor-LR, a conversational benchmark derived from the CANDOR corpus of 1,656 natural dyadic videoconferences. Our custom data preparation pipeline yields 713.5, 10.1, and 60.1 hours of training, validation, and test data, respectively. Evaluating pretrained AVSR models on Candor-LR reveals that audio-only accuracy drops sharply compared to LRS3, but visual cues compensate effectively, driving much larger performance gains on Candor-LR than on LRS3. Furthermore, training on this corpus significantly improves cross-domain robustness under both clean and noisy conditions, as its realistic conversational data captures broader audio-video features. We open-source our pipeline to ensure reproducibility, establishing Candor-LR as a challenging benchmark for conversational AVSR.
Read the full abstract

All authors Rishabh Jain, Aristeidis Papadopoulos, Zhaofeng Lin, Naomi Harte

Audio and Speech Processing

Teacher-Free Self-Distilled Consistency Trajectory Learning for Fast Speech Enhancement

Shuubham Ojha and Carol Espy-Wilson

Consistency trajectory models offer a route to fast, high- quality speech enhancement, collapsing the many reverse steps of diffusion-based enhancers into a handful. When instantiated on a Schrödinger bridge (SB), which pins the generative process to fixed clean and noisy endpoints, exist- ing consistency-trajectory enhancers (SBCTMs) still require a pretrained teacher to supply trajectory supervision, which raises training cost and ties the final quality to that of the teacher. We propose a teacher-free, self-distilled consistency- trajectory framework that removes the external teacher result- ing in a 5X reduction in per epoch training time. Our model is trained with a three-stage curriculum of clean speech pre- diction, a self-distilled shortcut objective, and perceptual fine-tuning with a multi-resolution short-time Fourier trans- form (MR-STFT) loss. Using the same NCSN++ backbone as SBCTM, our model attains a wide-band PESQ of 3.01, ES- TOI 0.87, and SI-SDR 19.07 dB on VoiceBank+DEMAND compared to 3.57, 0.87 and 12.8 dB for the teacher based model. Further, we find that a geometric schedule at low reverse step count maximizes perceptual quality, while a higher-step uniform schedule favors signal fidelity.
Read the full abstract

Audio and Speech Processing

AVSRBench: A Multi-Condition AVSR Benchmark

Rishabh Jain and Naomi Harte

While AVSR has achieved sub-1% word error rates on the standard LRS3 benchmark, its reliance on broadcast speech obscures whether this reflects true generalization or just domain adaptation. To investigate this gap, we evaluate three AVSR architectures across six conditions: controlled broadcast speech, fixed-grammar utterances, hyper-articulated Lombard speech, read speech from professional lipspeakers and non-professional speakers, and spontaneous multi-party video conversations. We find that visual-only performance deteriorates rapidly beyond broadcast domains, and audio-video fusion mainly benefits Lombard speech environments. Visual understanding degrades sharply at 90{\deg} profile views, with multimodal systems relying largely on acoustic fallback. Additionally, speaker articulation proves more critical than minor camera shifts, and LLM-based architectures suffer from poor out-of-domain generalization. Our work highlights a significant generalization gap in current AVSR research. To address this, we also introduce RoomReader-AV as a new benchmark for AVSR and release a unified data preprocessing pipeline to make comprehensive multi-condition evaluation accessible.
Read the full abstract

Audio and Speech Processing · Cross-listed from cs.SD

Unifying Score and Performance for Fine-Grained Music Understanding in Audio-Language Models

Milan Liessens Dujardin, Song-Ze Yu and Kevin Miao

Large audio language models (LALMs) have shown promising progress in broad music-understanding tasks such as tagging, retrieval, and captioning. Music understanding that requires finer hearing over both the content and how it is realized within a performance through dynamics, phrasing, articulation, time, and other performance techniques, however, remains at an earlier stage. Existing audio-language model (ALM) training pipelines typically rely on coarse, weakly grounded captions and therefore provide little support for learning these subtle nuances in music, limiting their ability to serve real-world applications in education or artistic practice. We therefore introduce MuNo-SP (Music Notation unifying Score and Performance), a text-based representation that jointly encodes score content and performance information. Building on MuNo-SP, we develop an automatic training-data generation pipeline that uses aligned scores and performances to produce long-form auditory analyses and musically informed question-answer pairs. We use this pipeline to construct MAESTROCaps, a classical piano dataset comprising 148 long-form performance analyses and 31,080 question-answer pairs derived from 148 aligned score-performance pairs. In a human evaluation, MuNo-SP analyses were preferred by majority vote over MIDI-only analyses for eight of nine excerpts. MuNo-SP also performed strongly on a benchmark of score-performance understanding, suggesting that integrating score and performance information enables more reliable and musically informative LALM supervision than a MIDI-only baseline.
Read the full abstract

Audio and Speech Processing

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

Taejin Park, Ivan Medennikov, Kunal Dhawan et al. (+3 more)

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.
Read the full abstract

All authors Taejin Park, Ivan Medennikov, Kunal Dhawan, Weiqing Wang, Jagadeesh Balam, Boris Ginsburg

Audio and Speech Processing · Cross-listed from cs.SD

Orukeet: Multilingual ASR with Frozen Gabor Kernels

Nathan Roll, Irene Yi, Büşra Marşan et al. (+6 more)

Orukeet replaces half of an adapted Parakeet encoder's temporal filters with 12,288 fitted Gabor kernels, freezes these replacements, and trains the remaining parameters on multilingual and multi-accent data. Final adaptation and checkpoint selection use LibriSpeech test-other. Across 20,146 FLEURS recordings in 25 languages, pooled word error rate (WER) falls from Parakeet's 11.01% to Orukeet's 9.85%, a 10.6% relative reduction. Orukeet has lower WER on 23 of the 25 languages. Orukeet outperforms Parakeet on 61 out of 74 tested splits, including LibriSpeech test-clean (1.46% vs. 1.53% WER), test-other (2.86% vs. 3.14%), and FLEURS English (3.82% vs. 4.28%). All comparisons decode the same audio with matched NeMo settings. The fitted kernels are stored as ordinary convolution weights, retaining Parakeet's architecture and inference operators.
Read the full abstract

All authors Nathan Roll, Irene Yi, Büşra Marşan, Vianney Grenez, Gabriel Stein, Momcilo Mrkaic, Pavle Padjin, Vladimir Zeljkovic, Calbert Graham

Audio and Speech Processing

SCNet: Enhancing GAN-based Speech Generation with Subband Condition Network and Magnitude-aware Phase Loss

Nan Xu and Mingxue Yang

Recent speech generation has been predominantly driven by GAN-based networks aimed at high-quality waveform synthesis from mel-spectrograms. However, these methods often operate as black-box models, leading to the loss of inherent spectral information. In this work, we propose SCNet, a GAN-based vocoder augmented with a Subband Condition Network to address this issue. Specifically, SCNet leverages a subband signal predicted by a lightweight condition network as prior knowledge. This subband signal is then transformed via STFT to obtain Fourier coefficients, which are integrated into the backbone for the enhanced reconstruction. Additionally, to mitigate the phase wrapping, we introduce a magnitude-aware phase loss that computes instantaneous phase errors weighted by the corresponding magnitude, emphasizing regions with higher energy. Experimental results demonstrate that SCNet achieves superior performance in both objective and subjective evaluations for high-quality speech generation.
Read the full abstract

Audio and Speech Processing

Over-Tightening-Aware Pseudo-Labeling for Tight-Boundary Speaker Diarization

Shota Horiguchi, Takanori Ashihara, Marc Delcroix et al. (+2 more)

Training speaker diarization models on loose labels, such as speech segments with padded boundaries or filled pauses, often results in similarly loose model outputs. To obtain tighter boundaries, pseudo-labeling based on the averaged outputs of causal and anticausal models has been proposed. However, since the pseudo-labels are estimation-based, they can suffer from over-tightening, which increases missed detections that can propagate as unrecoverable errors to downstream tasks. This paper carefully analyzes the causes of over-tightening and proposes three approaches to address them: (i) removing pause filling rather than padding, (ii) introducing a burn-in phase to mitigate missed detections near the beginning of causal and anticausal predictions, and (iii) making pseudo-label-based co-training aware of the non-causal model used for final inference. Experimental results show that the proposed method reduces missed detections caused by over-tightening and improves both diarization accuracy and downstream multi-talker ASR performance.
Read the full abstract

All authors Shota Horiguchi, Takanori Ashihara, Marc Delcroix, Naohiro Tawara, Alexis Plaquet

Audio and Speech Processing

SpeechAnnotator: A Context-Aware Multi-Agent Framework and Benchmark for Multidimensional Speech Annotation

Qirui Zhan, Shuiyuan Wang, Jingbin Hu et al. (+10 more)

Recent controllable speech generation requires training data with fine-grained annotations of speaker traits, prosody, emotion, paralinguistic cues, acoustic scenes, and context. Existing workflows often rely on manual correction, paid hosted multimodal services, or fixed processing chains, which limits large-scale data processing through annotation cost, external-service dependence, or weak cross-stage recovery. We introduce SpeechAnnotator, a locally deployable, context-aware multi-agent framework built entirely from open-source models and tools. Supporting frontend modules first obtain speaker-aware segments and final segment transcripts, while prior evidence extractors attach heterogeneous segment-level cues. Three specialist agents then collaborate through shared state: the Planning Agent converts local audio evidence, speaker history, neighboring segments, and recording-level context into field-specific contracts; the Labeling Agent performs contract-guided multimodal prediction for directly observable attributes; and the Review Agent runs a bounded review loop that checks evidence support and cross-segment consistency, triggering relabeling only for unsupported or inconsistent fields. To address the fragmentation of existing evaluation resources across isolated tasks and narrow-domain test sets, we introduce SpeechAnnotator-Bench (SA-Bench), containing 8.87 hours of human-annotated audio across nine source formats, together with SpeechAnnotator-Eval (SA-Eval), which separates Timeline-Eval for speaker-aware timeline recovery, Closed-Eval for finite-set attributes, and Open-Eval for open-ended attributes. Experiments and ablations show that SpeechAnnotator provides a locally deployable alternative to commercial audio-capable systems, while the bounded review loop improves multidimensional annotation through evidence- and context-aware field-level recovery.
Read the full abstract

All authors Qirui Zhan, Shuiyuan Wang, Jingbin Hu, Haoyu Zhang, Xiaming Ren, Jinrui Liang, Chaoren Yu, Bengu Wu, Yunxiang Chen, Houdun Liu, Su Feng, Liumeng Xue, Lei Xie

Audio and Speech Processing

NVV-Locator: From Transcript Tags to Acoustic Boundaries for Fine-Grained Nonverbal Vocalization Grounding

Yuang Cao, Bingshen Mu, Zhennan Lin et al. (+7 more)

Human speech includes nonverbal vocalizations (NVVs), such as laughter, sighs, breaths, and coughs, which convey affective and interactional information. Existing approaches typically represent NVVs as transcript-level tags, providing limited supervision for their waveform-time boundaries. We present NVV-Locator for fine-grained NVV temporal grounding. We first unify 26 NVV categories across public resources and construct large-scale timestamp-supervised training data through dual-LLM verification, transcript-guided forced alignment, and energy-based boundary refinement. We further introduce NVV-TimeBench, an expert-refined benchmark with 667 utterances and 1,094 events. NVV-Locator uses a non-autoregressive slot-filling architecture to jointly predict lexical timestamps, NVV categories, and event boundaries. On NVV-TimeBench, it achieves 71.0% Micro F1, 70.2% Macro F1, 80.4% Macro mIoU, and 59.6 ms Macro mMAE, outperforming the evaluated large audio model counterparts. Evaluation on an external corpus further demonstrates the cross-corpus generalization of NVV-Locator.
Read the full abstract

All authors Yuang Cao, Bingshen Mu, Zhennan Lin, Guojian Li, Haoyue Zhan, Jie Liu, Chuan Xie, Qiang Zhang, Liumeng Xue, Lei Xie

Audio and Speech Processing

Source-Adaptive Data Curation for Bilingual NVV-Aware ASR

Yuang Cao, Qirui Zhan, Jingbin Hu et al. (+7 more)

Nonverbal vocalizations (NVVs), such as laughter, sighs, breaths, and coughs, convey affective and interactional information that conventional automatic speech recognition (ASR) systems often discard. We present a bilingual Mandarin-English system for Track 1 of the NVVSpeech Challenge at ISCSLP 2026, which requires joint transcription of lexical content and 16 NVV categories at their transcript-relative positions. Our NVV-Aware Whisper adapts Whisper-medium through checkpoint-compatible vocabulary remapping, enabling lexical tokens and inline NVV tags to be decoded within a unified autoregressive sequence without expanding the vocabulary. To provide reliable and diverse supervision, we further introduce a source-adaptive data curation strategy that refines public NVV corpora through acoustic augmentation and multimodal LLM filtering, while mining spontaneous NVVs from in-the-wild media through automated preprocessing and annotation. Under the official bilingual evaluation protocol, the proposed system improves final score from 33.32 to 53.61, with ablations confirming the complementary benefits of the proposed data-curation components.
Read the full abstract

All authors Yuang Cao, Qirui Zhan, Jingbin Hu, Ziyu Zhang, Yunxiang Chen, Houdun Liu, Su Feng, Bengu Wu, Lei Xie, Liumeng Xue

Audio and Speech Processing

SphereVAE: Hyperspherical Latent Autoencoders for Robust Autoregressive Speech Representation Modeling

Haoyu Zhang, Jingbin Hu, Hanke Xie et al. (+8 more)

With the rapid development of speech generation technology, discrete codec representations have been widely used because they provide a stable prediction paradigm. In expressive speech generation, however, the quantization bottleneck of discrete codecs results in information gaps in fine-grained prosody, timbre, pronunciation, and frame-to-frame continuity. Continuous representations (e.g., VAE latents), by eliminating this constraint, have emerged as a more effective alternative for autoregressive modeling. Yet when continuous representations are used as autoregressive prediction targets, prediction errors can accumulate along the generation chain, causing latent drift and degrading long-form stability. To mitigate this problem, we propose SphereVAE, which constrains the VAE latent space to the unit hypersphere. SphereVAE defines a Power Spherical posterior on the hypersphere and regularizes the latent distribution toward a uniform prior, so that information is encoded mainly by directional variation, providing a bounded geometric target for autoregressive prediction and reducing the risk of norm drift. SphereVAE underperforms the standard VAE on reconstruction metrics due to reduced latent freedom. However, when integrated into VoxCPM for zero-shot TTS and long-text generation, it yields lower content error rates with comparable speaker similarity, and shows more stable long-range speaker consistency. These results indicate that an appropriate latent geometric constraint can effectively mitigate autoregressive error accumulation and drift in speech generation.
Read the full abstract

All authors Haoyu Zhang, Jingbin Hu, Hanke Xie, Qirui Zhan, Wenhao Li, Ziyu Zhang, Xiaming Ren, Yue Li, Xunyu Zhu, Zhipeng Chen, Lei Xie

Audio and Speech Processing

UniStream: Multi-Expert Residual Vector Quantization for 48 kHz Causal Streaming Audio Coding

Mingyu Zhao and Zhiyong Wu

We present UniStream, a fully causal 48 kHz neural audio codec for streaming speech, music, and environmental sounds. At its core is Multi-Expert Residual Vector Quantization (ME-RVQ), which replaces the single shared codebook in each residual quantization layer with four expert codebooks controlled by a deterministic Top-K router. Because routing decisions are derived solely from previously decoded quantized states, the decoder can reproduce the selected experts without transmitting expert identifiers, thereby expanding quantization capacity while adding 5.5M parameters. We further introduce an auxiliary Optimal Transport Conditional Flow Matching (OT-CFM) objective to regularize the quantized latent space during training. The flow module is removed entirely at inference and therefore incurs no runtime overhead. UniStream supports a 12 kbps Top-1 mode and a 22.5 kbps Top-2 mode within a causal 48 kHz encoder-decoder framework, while achieving real-time GPU inference. To complement narrow-band speech metrics, we report 48 kHz ViSQOL audio mode, ViSQOL speech mode, standard VGGish-FAD, DNSMOS P.835, and higher-rate reference comparisons with Opus and EnCodec. At 12 kbps, UniStream-Top1 achieves PESQ and UTMOS scores comparable to EnCodec while reducing speech Mel-D from 13.07 to 8.21. At 22.5 kbps, UniStream-Top2 achieves a ViSQOL speech-mode score of 4.67 and an environmental audio-mode score of 3.96, exceeding all evaluated systems operating at 12 kbps or below in the latter setting. It also comes within 0.03 MOS-LQO of Opus at 24 kbps on speech in ViSQOL audio mode. Ablation studies confirm that ME-RVQ is the primary source of quality improvement, whereas OT-CFM provides perceptual gains on speech with a mild trade-off in spectral distortion.
Read the full abstract

Audio and Speech Processing · Cross-listed from cs.CL

StreamAlign: Streaming Text-Aligned Speech Tokenization

Kang-wook Kim, Jinyoung Park, Jinsoo Kim et al. (+3 more)

Text-aligned speech tokenization methods have emerged to better align speech tokens with LLM token spaces, enabling more effective utilization of pretrained LLMs. However, they rely on offline automatic speech recognition (ASR), leading to two key limitations: (i) the need for complete utterances before tokenization, precluding real-time streaming, and (ii) vocabulary mismatch between ASR and LLMs, which reduces acoustic granularity from the subword to the word level. We introduce StreamAlign, a text-aligned speech tokenization framework that enables streaming tokenization for real-time speech-text joint modeling. StreamAlign performs online speech-text alignment by combining character-level RNN-Transducer alignment with word-level ASR guidance, mitigating ASR-LLM vocabulary mismatch while preserving recognition accuracy. A proactive word boundary classifier anticipates word completion at chunk boundaries, reducing tokenization latency from 560 ms to 270 ms. On LibriSpeech, StreamAlign achieves the lowest WER and highest UTMOS among evaluated tokenizers. Furthermore, StreamAlign-SLM, a spoken language model trained on StreamAlign units, outperforms other end-to-end spoken language models in speech continuation while achieving the strongest overall consistency on SALMon and spoken StoryCloze.
Read the full abstract

All authors Kang-wook Kim, Jinyoung Park, Jinsoo Kim, Sehun Lee, Sang Hoon Woo, Gunhee Kim

Audio and Speech Processing · Cross-listed from stat.ML

Why Learning Rediscovers the Closed-Form Diagonal Regularizer

Jeahn Han and Pyojin Kim

Recovering modal amplitudes from a few sensors requires regularization, and the shape of the penalty decides how strongly each mode is shrunk. The best shape depends on the truncation noise that discarded modes add to every measurement, which is unobserved and could be room-specific. We identify a diagonal saturation principle: for a single snapshot, isotropic truncation noise makes the Bayes-optimal Tikhonov shape a closed-form power law Gamma_k proportional to lambda_k^|s|, set by the prior alone and independent of the domain. The off-diagonal anisotropy equals the Herfindahl index H of the discarded-mode power exactly, Weyl's eigenvalue counting law fixes the number of discarded modes and hence H, and Berry's random-wave conjecture enters only through a diagonal term D, which we measure directly. Together they predict an approximately flat loss landscape over the penalty exponent, which leaves a learned diagonal regularizer little to gain from tuning the exponent per room. On simulated acoustic rooms the closed form stays within 5.83% of a per-room power-law oracle across observation windows, and three learned diagonal architectures track its error, the closest within a fraction of a point and none more than 3pp above it, while learning qualitatively different spectra. In the truncation regime no tested method consistently improves on the closed form, including Learned Iterative Ridge, which couples modes across layers. The framework extends to heat diffusion through a known Green's-function correction with no new free parameters.
Read the full abstract

Tuesday 8 September

Audio and Speech Processing

Language Orthogonalization of Self-Supervised Speech Representations for Cross-lingual Parkinson's Detection

Minu Kim, Eunjung Yeo, Kwanghee Choi et al. (+1 more)

Self-supervised speech models (S3Ms) provide powerful representations for Parkinson's disease (PD) detection, making cross-lingual transfer attractive for languages lacking labeled patient speech. However, these representations also encode language identity, which can confound this transfer: without target-language PD speech, classifiers may separate languages rather than pathology, yielding high specificity but low sensitivity on target patients. We propose language orthogonalization, a closed-form ridge residualization of S3M features against external VoxLingua107 language embeddings, fitted using only healthy-control (HC) speech. By removing language-predictable components while retaining pathology-related variation, it produces a less language-dependent geometry in which HC representations concentrate while PD representations disperse. Across five S3M backbones, three speech tasks, and three target languages, our method consistently improves cross-lingual PD-detection performance while correcting the high-specificity/low-sensitivity failure.
Read the full abstract

All authors Minu Kim, Eunjung Yeo, Kwanghee Choi, June-Woo Kim

Audio and Speech Processing

Multimodal Duplex Interaction Agent

Orantqing, Shengpeng Ji, Junlong Tong et al. (+19 more)

In this work, we present Gander, a native multimodal duplex interaction model that builds on MiniCPM-o 4.5 and is further adapted for realtime interaction with an asynchronous agent loop. In contrast to conventional turn based systems, Gander continuously processes streaming user inputs, enabling full-duplex interaction in both everyday conversations and complex workflow agent scenarios. Users can interrupt an ongoing response, while the model can proactively provide intermediate feedback or ask follow up questions. To natively support these capabilities, Gander adopts two key architectural designs: 1) a Cerebellum-Brain collaborative framework, Cerebellum is responsible for realtime interaction while the Brain handles complex reasoning and higher level agentic tasks. The two components interact continuously through tool calling and the agent orchestration runtime. 2) The Cerebellum is built upon a streaming Thinker-Talker architecture, where user inputs and model outputs are flattened into an ordered token stream at the chunk level. We evaluate Gander across conversational ability, interactive capability, understanding, and tool assisted task execution. Internal human evaluations show that Gander maintains natural and expressive spoken dialogue, while benchmark results demonstrate effective turn taking capability and encouraging results on spoken question answering and related understanding tasks. Gander also supports a range of challenging interaction settings, including background noise interference, multi-party interactions, and backchannel communication. While our current evaluation focuses on tool assisted settings, broader long horizon agent tasks and more diverse deployment conditions remain promising directions for further study. We release Gander together with its models, code, and data to facilitate further research and development in the community.
Read the full abstract

All authors Orantqing, Shengpeng Ji, Junlong Tong, Jialong Zuo, Dongjie Fu, Di Cao, Yangzhuo Li, Shangda Wu, Franz, Evan, Theron Veyra, Changhao Pan, Jingyu Lu, Dongchao Yang, Zhifei Xie, Yang Tan, Xiaoyu Shen, Xiaoda Yang, Wenfu Wang, Teddy Sun, Steve Yves, Zhou Zhao

Audio and Speech Processing · Cross-listed from cs.SD

From Scores to Evidence: Auditable Decisions Can Improve Speech Deepfake Detection

Mengzhe Geng, Yujia Lu, Manuela Kunz et al. (+1 more)

Speech deepfake detectors usually emit one score per utterance, but a borderline score does not reveal why two examples differ during retrospective error analysis. We ask whether a final score can be calibrated from component fields while keeping those fields visible for inspection. We build a decision record with a passive detector score and a score from a probe applied to a marked copy. It also includes retrieval support held out of the evaluated family, a margin from a support-set profile, and raw neighbor closeness. A cross-fit calibrator combines these fields and two differences between raw scores into one final score. On matched ASVspoof development data, the calibrated record reduces equal error rate (EER) by 3.48 percentage points relative to the fixed retrieval-augmented rule. It reaches 8.43% EER, whereas a passive WavLM baseline reaches 6.71% on the same subset. The record is therefore not the strongest detector in this comparison. Its value is to retain inspectable component fields while producing one scalar score for retrospective diagnosis.
Read the full abstract

All authors Mengzhe Geng, Yujia Lu, Manuela Kunz, Patrick Littell

Audio and Speech Processing

Interpreting Dolphin Vocal Sequences via Multiple Sequence Alignment

Daniel Kohlsdorf, Denise Herzing and Thad Starner

Dolphin communication understanding is essential for uncovering the linguistic complexity and social structures of wild pods. We adapt the ClustalW bioinformatics algorithm to analyze continuous acoustic data, treating vocalizations as high-dimensional spectral feature vectors. By replacing discrete scoring with a continuous Gaussian kernel similarity measure, our framework generates Multiple Sequence Alignment (MSA) visualizations that reveal shared structural patterns. These alignments highlight temporal motifs such as synchronized burst pulses in aggressive contexts that are difficult to detect through standard spectrogram inspection.
Read the full abstract

Audio and Speech Processing · Cross-listed from cs.HC

Rescuing Performance from the Demo: Co-Designing Drum Gesture Mappings with a Percussionist

Jordie Shier, Teresa Pelinski, Charalampos Saitis et al. (+2 more)

Augmenting instruments with sensors and neural network mappings is a well-explored digital musical instrument design approach. While augmentations can create new expressive opportunities, they also exert aesthetic influence and can constrain musicians' gestural language, which, if left unchecked, can lead to technological capture. To examine this, we conducted a study with a professional percussionist, co-developing a gesture mapping toolkit and recording a ten-track album. Drawing on the concept of productive dissonance, our study aimed to hold the musician's aesthetic in tension with technological constraints. This, along with a practice-based reflective approach, supported the development of a continuous gesture recognition method for percussive mapping and surfaced insights into the design process. We identify knowing-when as a form of tacit knowledge that supported productive dissonance, and raise an open question: absent a musician's broader social context, how do we know whether a technology's influence is genuinely supporting their practice?
Read the full abstract

All authors Jordie Shier, Teresa Pelinski, Charalampos Saitis, Andrew Robertson, Andrew McPherson

Audio and Speech Processing

Spatial Audio Coding Through Relative Room Impulse Response Estimation

Nour Bouayed, Adrien Llave, Jérôme Daniel et al. (+1 more)

Immersive virtual listening relies on spatial audio technologies such as Higher-Order Ambisonics (HOA), which represent sound scenes as multichannel signals. As the desired spatial resolution increases, so does the number of channels, making efficient compression essential for transmission over bandwidth-limited networks. Moreover, to facilitate deployment by network operators, the target bitrate for immersive audio coding should ideally remain close to the 25 kbps currently allocated to VoLTE audio services. State-of-the-art parametric codecs, such as the recently standardized Immersive Voice and Audio Services (IVAS) codec, achieve compression by transmitting spatial metadata together with a reduced number of transport channels. However, recent studies have shown that IVAS performance degrades on reverberant content, particularly at low bitrates, a limitation that suggests its inability to accurately model room acoustics. In this paper, we propose a novel HOA coding scheme based on the explicit and blind estimation of the Relative Spatial Room Impulse Response (ReSRIR), using a beamformed version of the HOA signal as a reference signal. By exploiting the structure and sparsity of the estimated ReSRIR, we derive an efficient parametric representation for immersive audio coding. Experimental evaluations show that the proposed method achieves higher compression than IVAS in the single-transport-channel regime, while maintaining comparable to slightly better quality.
Read the full abstract

All authors Nour Bouayed, Adrien Llave, Jérôme Daniel, Pascal Scalart