Peer Revenue Fully funded

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

Monday 24 August

Audio and Speech Processing

EmoTra-TTS: Smooth Intra-Utterance Emotion Transitions for Speech Synthesis

Tianchi Liu, Zeyang Song, Tianrui Wang et al. (+3 more)

Psychological research on emotion dynamics has established that human affect is a continuous, evolving process: emotions rise, decay, and transition within seconds. Current emotional text-to-speech (TTS) systems, however, condition on a single discrete label or static embedding per utterance, fundamentally misaligning with the temporal nature of affect. While recent LLM-based TTS systems may implicitly vary prosody through text understanding, such variation is neither explicitly controllable nor precise enough for targeted intra-utterance transitions. We address three challenges: (1) a multi-pass flow blending pipeline synthesizes frame-aligned transition audio, circumventing the scarcity of natural intra-utterance transitions; (2) dual-stage Valence-Arousal-Dominance (VAD) conditioning guides prosodic planning in the LLM and acoustic realization in the flow decoder via frame-level VAD embeddings; (3) direction-magnitude decoupled injection structurally separates emotion direction from injection magnitude, preventing content degradation. EmoTra-TTS adds only +0.43% parameters with no latency overhead, achieves 30%-87% relative improvement on emotion transition quality, corroborated by 64.4%-79.5% overall win rates in pairwise preference tests against four SOTA baselines and two commercial systems.
Read the full abstract

All authors Tianchi Liu, Zeyang Song, Tianrui Wang, Zhipeng Li, Chenglin Xu, Yiwen Guo

Audio and Speech Processing

The ISCSLP 2026 Real-World Audio-Visual Speech Enhancement Challenge: A Benchmark with Natural Mixtures and Degraded Video

Kai Li, Wenze Ren, Junjie Li et al. (+11 more)

Audio-visual speech enhancement (AVSE) uses a target speaker's visible articulation to recover that speaker's voice from overlapped speech. Yet most evaluation protocols rely on synthetic mixtures and reliable video. The ISCSLP 2026 Real-World AVSE Challenge addresses both gaps. Track~1 combines naturally recorded two-talker mixtures, which lack a clean reference, with reference-available remixes of the same speakers; Track~2 additionally degrades the target video in five ways and adds 3-m far-field recordings. Sixteen and twelve teams were ranked on speaker-disjoint test data by rank averaging over waveform fidelity, predicted quality, transcription accuracy, and speaker similarity. On Track~1 remixes, the best system reaches 12.7~dB SI-SDR and 0.85 STOI, but natural recordings remain harder: even the lowest CER rises from 9.0% to 14.7%. The leading systems use video mainly for speaker attribution rather than signal reconstruction, and the top two lose under 0.5~dB SI-SDR on Track~2. UTMOS and DNSMOS rank systems differently from the other metrics, so no single metric captures target-speech recovery. We release the baselines, evaluator, and official results.
Read the full abstract

All authors Kai Li, Wenze Ren, Junjie Li, Cheng Yu, Peijun Yang, Chien-yu Huang, Haibin Wu, Szu-Wei Fu, Wen-Chin Huang, Hsin-Min Wang, Xiaolin Hu, Ming Li, Yu Tsao, DeLiang Wang

Audio and Speech Processing

Unsupervised Speech Recognition at the Syllable Level

Liming Wang, Kai-Wei Chang, Kunio Kashino et al. (+3 more)

Training speech recognizers with unpaired speech and text – known as unsupervised speech recognition (UASR) – is a crucial step toward extending ASR to low-resource languages in the long-tail distribution and enabling multimodal learning from non-parallel data. However, existing approaches based on phones often rely on costly resources such as grapheme-to-phoneme converters (G2Ps) and struggle to generalize to languages with ambiguous phoneme boundaries due to training instability. In this paper, we address both challenges by introducing a syllable-level UASR framework based on masked language modeling, which avoids the need for G2P and the instability of GAN-based methods. Our approach achieves up to a 40% relative reduction in character error rate (CER) on LibriSpeech and generalizes effectively to low-resource languages that have remained particularly difficult for prior methods. Code is publicly available\footnote{https://github.com/cactuswiththoughts/SylCipher}.
Read the full abstract

All authors Liming Wang, Kai-Wei Chang, Kunio Kashino, David Harwath, Mark Hasegawa-Johnson, James R. Glass

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

Better Retrieval, Worse Robustness: How Multi-hop RAG Amplifies Upstream ASR Errors

Zhenghua Bao

Speech-based applications pass spoken queries through automatic speech recognition (ASR) before any retrieval module, so ASR errors enter the pipeline as a fixed upstream constraint. We empirically test whether two extensions to standard retrieval-augmented generation (RAG), entity-graph linking and iterative reformulation, absorb or amplify these errors. Using four English accents synthesized through neural TTS, we evaluate four RAG configurations on three multi-hop QA benchmarks (HotpotQA, 2WikiMultiHopQA and MuSiQue) against a clean-text oracle. Although the structurally richer configurations generally retain higher absolute F1 under ASR input, both extensions amplify the error: the F1 gap from clean text to the highest-WER accent is 36-67% larger under their combination than under naive dense retrieval, on all three benchmarks. The dominant failure mode is corruption of one or more query entities, accounting for 87-96% of degradation cases on 2WikiMultiHopQA across all four methods. Two lightweight surface-form mitigations leave most of the gap intact, indicating that downstream retrieval structure amplifies remaining entity errors. We release code and data at https://github.com/Continuum-AI-Corp/spoken-multihop-rag .
Read the full abstract

Audio and Speech Processing

DiaScriber: A Speech LLM for Joint Diarization and Transcription in Multi-Speaker Scenarios

Bingshen Mu, Xian Shi, Xiong Wang et al. (+6 more)

Multi-speaker automatic speech recognition (MSASR) aims to jointly predict content transcriptions, speaker identities, and timestamps, thereby addressing the key question of "who spoke what and when" and holds substantial practical value in real-world multi-speaker scenarios. However, MSASR still encounters considerable challenges in the presence of fast turn transitions, overlapping speech, and complex, diverse multi-speaker scenarios. In this work, we propose DiaScriber, an end-to-end multi-speaker diarization and transcription model built on a speech large language model. We first construct diverse data pipelines to cover a wide variety of multi-speaker scenarios and their complexities, including validation and refinement, turn-transition and overlapping-speech simulation, and multimodal annotation. Furthermore, DiaScriber is developed based on the pretrained version of Qwen3.5-Omni through a three-stage training strategy involving continual pretraining, supervised fine-tuning, and reinforcement learning. Experiments show that DiaScriber achieves superior performance over comparison methods across extensive multi-speaker scenario test sets and demonstrates outstanding generalization ability in unseen multi-speaker scenarios.
Read the full abstract

All authors Bingshen Mu, Xian Shi, Xiong Wang, Zhifang Guo, Ting He, Xize Cheng, Yu Xi, Jin Xu, Lei Xie

Sunday 23 August

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

MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models

Yize Li, Ningyuan Yang, Sile Yin et al. (+6 more)

Large audio-language models (LALMs) have shown promising progress in understanding speech, music, and general sound events, yet their ability to reason about how audio signals are degraded remains underexplored. Existing benchmarks primarily evaluate semantic understanding, event recognition, or high-level audio reasoning, leaving a basic question unanswered: Do LALMs understand the differences in audio quality? We introduce MRMAD, a Multi-Round Multi-Audio Degradation benchmark for evaluating audio degradation perception and understanding in LALMs. MRMAD spans speech, music, and sound, and frames evaluation as multi-turn dialogues across multiple audio inputs, requiring models to identify types of degradation, compare severity, and perceive corruption changes across turns. Unlike current single-turn audio-language benchmarks, MRMAD evaluates whether LALMs can maintain consistent degradation hypotheses with new evidence and comprehend low-level acoustic phenomena over multi-turn dialogues. Through a systematic evaluation of 18 representative LALMs from non-thinking to reasoning and Omni models, we find that current models often recognize coarse content while failing to diagnose, compare, or reason about degradations reliably. Human evaluations further reveal a significant perception gap between LALMs and human listeners. MRMAD thus exposes a critical yet overlooked aspect of audio-language understanding and provides a diagnostic foundation for building future LALMs that are robust to real-world acoustic conditions.
Read the full abstract

All authors Yize Li, Ningyuan Yang, Sile Yin, Sindhuja Thogarrati, Sung-En Chang, Andrew C. Singer, Xue Lin, Chuan-Che Huang, Shuo Zhang

Audio and Speech Processing

Mitigating Speaker Leakage in Cascaded Multi-talker ASR with Diarization-based Transcript Correction

Hermann Yepdjio Nkouanga, Minwei Luo, Maggie Wigness et al. (+1 more)

While cascaded multi-talker ASR (MT-ASR) leverages state-of-the-art foundation models, its performance is often capped by speaker leakage during separation. Prior correction strategies primarily focus on lexical re-labeling for speaker attribution. We propose a complementary pruning-based paradigm that robustly identifies and removes leakage artifacts. Our method utilizes a pre-trained speaker diarization model as a multimodal verifier to prune transcribed segments satisfying a tripartite consensus of temporal containment, lexical cross-validation, and temporal alignment. Results on LibriMix, LibriSpeechMix, and the AMI Meeting corpus show our algorithm consistently reduces cpW ER across diverse overlap conditions. Specifically, on subsets with high speaker leakage, our method achieves relative cpW ER reductions of up to 29%, highlighting its effectiveness in enhancing the reliability of cascaded MT-ASR transcripts in complex acoustic environments.
Read the full abstract

All authors Hermann Yepdjio Nkouanga, Minwei Luo, Maggie Wigness, Suresh Singh

Friday 21 August

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

Grounded Decoding for Autoregressive Speech Enhancement via Adaptive Code-Space Grounding and Local LLM Refinement

Hao Shi, Yuan Gao, Zhaoheng Ni et al. (+4 more)

Large language model (LLM)-based autoregressive speech enhancement (SE) produces natural speech using learned clean-speech priors, but may hallucinate content unsupported by the input. Deterministic SE better preserves observation-coupled evidence, yet often retains residual noise or local distortion. We propose an evidence-grounded generative SE framework that uses a deterministic estimate as imperfect evidence. A Whisper-guided DPRNN produces an enhanced waveform, which is blended with the observation and tokenized into a discrete evidence sequence. The evidence conditions an autoregressive clean-speech token generator and is reused during decoding through Code-Space Grounding (CSG), which penalizes candidates according to their Hamming distance in the factorized finite-scalar-quantized (FSQ) space. Because the appropriate grounding strength depends on acoustic difficulty, we introduce SNR-Conditioned CSG (SNR-CSG), which maps a calibrated residual-SNR estimate to an utterance-level strength and constructs an adaptive grounded anchor. Although grounding improves content fidelity, the anchor may retain local acoustic defects inherited from the evidence. Since such defects are predominantly local in the FSQ space, nearby tokens may provide better acoustic realizations without large departures from the observation-supported trajectory. We therefore propose Grounded Neighborhood Refinement with LLM ranking (GNR-LLM). It performs one additional teacher-forced pass conditioned on the grounded-anchor history, intersects the LLM top-$K$ candidates with a local FSQ Hamming neighborhood. Experiments on in-domain, controlled-SNR, and DNS no-reverb conditions show that SNR-CSG provides robust automatic grounding, while GNR-LLM substantially improves low-SNR perceptual quality without sacrificing content fidelity.
Read the full abstract

All authors Hao Shi, Yuan Gao, Zhaoheng Ni, Junyi Peng, Gongping Huang, Yu Tsao, Xugang Lu

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

MusPyExpress: Extending MusPy with Enhanced Expression Text Support

Phillip Long, Hao-Wen Dong, Julian McAuley et al. (+1 more)

Current work in modeling symbolic music primarily relies on representations extracted from MIDI-like data. While such formats allow for modeling symbolic music as sequences of notes, they omit the large space of symbolic annotations common in western sheet music broadly known as expression text, such as tempo or dynamics, which specify time- and velocity-dependent controls on the musical composition and performance. To alleviate this gap, we present MusPyExpress, an extension to the popular symbolic music processing library MusPy that enables the extraction of expression text along with symbolic music for downstream modeling. Utilizing this extension, we parse the PDMX dataset to illustrate the wealth of expression text available in MusicXML datasets. Additionally, we introduce multiple generative tasks, including joint expression-note generation, expression-conditioned music generation, and expression tagging, that take advantage of this additional notational information.
Read the full abstract

All authors Phillip Long, Hao-Wen Dong, Julian McAuley, Zachary Novack

Audio and Speech Processing

Separating Voice from Age in COPD Screening

George P. Kafentzis and Nikoletta Arvaniti

Voice has been proposed as a low-cost screening signal for chronic obstructive pulmonary disease (COPD). COPD is strongly age-associated and voice changes with age, thus such results admit a trivial alternative explanation. We re-evaluate a public sustained-phonation corpus ($1246$ recordings, $68$ participants) under a strictly participant-level protocol. We therefore evaluate on repeatedly drawn age-matched cohorts and report the discrimination achieved by the confounders themselves on those same cohorts. Where raw (unmodelled) age ($0.510$ $[0.469, 0.551]$) and raw gender ($0.479$) are both measured at chance, acoustic models excluding age retain ROC-AUC $0.717$ $[0.552, 0.859]$ and average precision $0.747$ $[0.581, 0.892]$ against a one-to-one baseline of $0.5$, whereas models containing age fall to $0.531$–$0.679$. The separation is reproduced by two further learners with fixed hyperparameters. Two findings have broader methodological implications: models trained with age transfer less effectively to an age-balanced target cohort than otherwise identical models trained without age, and fourteen classical voice-quality and perturbation measures achieve comparable discrimination to a $55$-dimensional combined representation. We conclude that a non-age acoustic signal is present, that confounding by recording conditions cannot be excluded from the released features, and that the evaluation protocol in standard use cannot distinguish these possibilities.
Read the full abstract

Audio and Speech Processing

TurboBias 2.0: Streaming Context-Biasing for Production-Efficient ASR Systems

Vladimir Bataev, Lilit Grigoryan, Andrei Andrusenko et al. (+3 more)

Contextualization is essential for production automatic speech recognition (ASR) systems, where user-provided phrases must be recognized accurately under strict latency constraints. Although many context-biasing methods improve recognition accuracy, they often do not address the practical requirements of modern production ASR systems: streaming inference, efficient batched decoding, user-specific context lists, and low runtime overhead. We propose TurboBias 2.0, a production-oriented framework for efficient phrase boosting in Transducer-based ASR systems. The framework extends GPU-accelerated TurboBias with a case-insensitive boosting graph and per-stream batched decoding, allowing each utterance in a batch to use an independent context-biasing configuration. This enables personalized context biasing for multiple simultaneous users without sharing or mixing their context lists. The proposed framework supports both offline and streaming inference and can be used with greedy and beam-search decoding. Experiments show that TurboBias 2.0 improves contextual phrase recognition while preserving low latency and high throughput.
Read the full abstract

All authors Vladimir Bataev, Lilit Grigoryan, Andrei Andrusenko, Nikolay Karpov, Vitaly Lavrukhin, Boris Ginsburg

Audio and Speech Processing

SlimDiffuSE: Towards Efficient Diffusion-Based Speech Enhancement using Slimmable Networks

Nagashree K. S. Rao, Shrishti Saha Shetu, Mohamed Elminshawi et al. (+2 more)

Diffusion-based models are emerging in the speech enhancement domain and are achieving state-of-the-art performance across various benchmark datasets. A major downside of diffusion models is that data generation requires many evaluations of a typically large neural network, which results in high overall complexity. In this work, we propose a slimmable diffusion model that employs adaptive network widths throughout the data generation process to reduce computational cost. By using a greedy search algorithm to optimize the network width schedule, our method achieves performance comparable to baseline diffusion models with significantly reduced computational complexity. Notably, our approach reduces the computational complexity by up to $87.5\%$ without a significant drop in objective metrics, such as perceptual evaluation of speech quality (PESQ) and SI-SDR.
Read the full abstract

All authors Nagashree K. S. Rao, Shrishti Saha Shetu, Mohamed Elminshawi, Emanuël A. P. Habets, Andreas Brendel

Audio and Speech Processing

{\mu}Net: Ultra-Low-Memory and Low-Complexity Speech Enhancement for Embedded Digital Signal Processors

Shrishti Saha Shetu, Jose Miguel Martinez Aponte, Nagashree K. S. Rao et al. (+3 more)

Speech enhancement on embedded digital signal processors (DSPs) imposes strict constraints on memory footprint, computational complexity, latency, and support for integer operations. Although recent DNN-based approaches have addressed these challenges individually, no unified framework in the literature simultaneously addresses all these requirements for practical deployment. In this work, we propose {\mu}Net, an ultra-low-memory, low-complexity, and low-latency end-to-end DNN model. The proposed method requires only $90$~KB of static memory and $28$~MMACs, while supporting an algorithmic latency as low as $4$~ms with performance comparable to state-of-the-art methods of similar complexity. Our experiments demonstrate that {\mu}Net is compatible with neural accelerators and supports full integer-arithmetic operations on consumer DSP platforms such as Cadence Tensilica HiFi 4/5.
Read the full abstract

All authors Shrishti Saha Shetu, Jose Miguel Martinez Aponte, Nagashree K. S. Rao, Sharvin Vittappan, Oliver Thiergart, Emanuël A. P. Habets

Audio and Speech Processing

Training DeepFilterNet with Accurate Room Acoustic Simulations Improves Single-Channel Speech Enhancement

Alessia Milo, Georg Götz, Steinar Gu{\dh}jónsson et al. (+3 more)

We investigate how the realism of synthetic room impulse response (RIR) datasets affects the training of DeepFilterNet3 for single-channel speech enhancement. We compare a DNS4 image-source-method (ISM) RIR dataset with a higher-acoustic-fidelity dataset generated using hybrid wave-based and geometrical acoustics simulation. Rather than isolating individual simulation factors, we compare complete RIR generation pipelines while keeping the enhancement model unchanged. Models are evaluated on unseen measured RIRs using objective speech enhancement metrics and downstream automatic speech recognition (ASR). Training with the higher-fidelity dataset consistently yields modest improvements in objective metrics and substantially lower ASR word error rates than the ISM dataset. Although the experiments do not attribute these gains to individual modelling components, they show that increasing the overall realism of synthetic acoustic training data improves the generalization of DeepFilterNet3 to unseen measured environments.
Read the full abstract

All authors Alessia Milo, Georg Götz, Steinar Gu{\dh}jónsson, Daniel Gert Nielsen, Jesper Pedersen, Finnur Pind

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

A Regularized Block Diagonal RLS Algorithm for Acoustic Echo Cancellation

Ruibin Hou, Chenggang Zhang and Yufeng Diao

While the recursive least square (RLS) algorithm is widely used in adaptive filtering applications like acoustic echo cancellation (AEC) due to its fast convergence rate, its high computational complexity severely limit its practical deployment for long filters. In this paper, a regularized block-diagonal RLS (RBD-RLS) algorithm is proposed to address these challenges. By approximating the inverse covariance matrix as a block-diagonal structure, RBD-RLS simplifies the update process into independent parallel computations of sub-blocks, effectively reducing the computational complexity. Additionally, Tikhonov regularization is applied to each sub-blocks for enhance numerical stability. A series of experimental results demonstrate that RBD-RLS maintains good convergence while significantly reducing computational complexity. Moreover, it still exhibits relative robustness in real-world scenarios.
Read the full abstract

Thursday 20 August

Audio and Speech Processing

$TCP_\alpha$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval

Parampreet Singh, Anushka Singh, Sumit Kumar et al. (+1 more)

Deep neural networks are often overconfident, assigning high confidence even to incorrect predictions. Consequently, users lack a reliable signal for deciding when a prediction can be trusted. Post-hoc confidence estimation addresses this by training a lightweight auxiliary head over a frozen classifier. Existing targets, however, suffer from inherent ambiguity: they assign overlapping confidence values to correct and incorrect predictions, while errors near the decision boundary receive confidence scores indistinguishable from correct predictions. In this work, we propose $TCP_\alpha$, a novel confidence target that resolves these limitations by introducing a margin-controlled penalty for misclassified samples. We prove that $TCP_\alpha$ guarantees complete separation between the target values of correct and incorrect predictions, with a separation margin that is independent of the number of classes and increases monotonically with the penalty parameter. Since accurate classifiers naturally produce very few errors, learning these targets results in a severely imbalanced regression problem. We therefore present a systematic study of training strategies for learning under this imbalance and identify an effective training configuration through extensive ablation studies. We evaluate the proposed approach on rāga identification, investigate its robustness under domain shift, and further validate it on frame-wise ornamentation detection without modifying the selected configuration. Across all settings, $TCP_\alpha$ consistently outperforms existing confidence targets for failure prediction. Rejecting only the least-confident 8% of predictions improves the base model's macro-F1 from 0.89 to 0.98, while fine-tuning the confidence head with only 5% labeled samples from a new corpus effectively restores performance under domain shift.
Read the full abstract

All authors Parampreet Singh, Anushka Singh, Sumit Kumar, Vipul Arora

Audio and Speech Processing

Explainability by Design: Structured Kolmogorov-Arnold Networks over Probabilistic Attributes for Speech Deepfake Source Tracing

Hoang H. Pham, Manasi Chhibber and Tomi H. Kinnunen

Modern speech synthesizers can produce highly realistic speech, making source tracing (i.e. identifying the generator behind a spoofed utterance) increasingly important for forensics, online content provenance, and platform accountability. Building on our prior work on transparent probabilistic attributes, which represent utterances as probability distributions over synthesizer sub-components, we extend speech deepfake source tracing with two key ingredients: multi-task training of the probabilistic attribute extractors and a structured Kolmogorov–Arnold Network (KAN) for attack classification. The probabilistic features are estimated jointly with a multi-task learning module built on a shared AASIST or SSL-AASIST countermeasure backbone. The resulting probabilistic feature embedding is classified by a structured KAN whose topology follows known attribute-to-attack relationships. This provides interpretability by construction: the architecture reflects the generative hierarchy of attacks, while KAN feature-importance scores quantify each probabilistic feature's contribution without post-hoc explainers such as SHAP. On ASVspoof2019-attr-17, the extended framework achieves balanced accuracies above 99% for all seven probabilistic feature extractors, with EERs of 0.16% to 0.07%, and 99.64% balanced accuracy with 0.11% EER for 17-class attack classification. Our revised model outperforms the earlier two-stage baselines, in addition to demonstrating reliable interpretability, with importance scores consistent with SHAP values, and stable results across batch sizes. These findings highlight the potential of structured KAN for speech deepfake source tracing that is both accurate and interpretable by design. For transparency and reproducibility, our codebase is publicly available: https://github.com/HoangHPham/KAN-Probabilistic-Deepfake-Attribution.
Read the full abstract

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

Tracking the Trend in How Speech Synthesizers Deceive People

Milan Šalko, Anton Firc, Kamil Malinka et al. (+4 more)

Advances in speech synthesis have made deepfake audio highly realistic. Earlier studies reported 70-80% human detection accuracy, but relied primarily on older synthesizers. We compare human detection for three selected voice synthesis tools released in 2019, 2022, and 2024 with 82 IT professionals, and benchmark humans against six pretrained detectors on the same material. For fully synthetic speech (full spoofs), the F1 score drops from about 90% for RTVC and YourTTS to 48% for ElevenLabs, although listeners were explicitly warned that deepfakes were present. For partial spoofing, where only one sentence of an utterance is altered, strict accuracy falls to 9%, and listeners classify the synthetic sentence as bona fide 77% of the time. Humans and detectors fail in complementary ways, and neither reliably localizes short manipulations. Additionally, listeners increasingly mislabel bona fide speech as fake, eroding trust in unmanipulated audio. These findings show that human perception alone is unreliable for the selected modern and partial-spoof conditions and motivate procedural verification, provenance, watermarking, and segment-level detection.
Read the full abstract

All authors Milan Šalko, Anton Firc, Kamil Malinka, Vojtěch Staněk, Martin Perešini, Filip Pleško, Jakub Reš

Audio and Speech Processing

Listening Forward: Next Patch Embedding Prediction Enables Scalable Audio Learners

Umberto Cappellazzo, Xubo Liu, Stavros Petridis et al. (+1 more)

Self-supervised learning (SSL) has driven substantial progress in audio representation learning, though existing methods have increasingly relied on elaborate pre-training recipes to reach competitive performance. A markedly different pre-training philosophy underpins the most influential progress in language modeling and, more recently, in visual representation learning: rather than train encoders as static feature extractors, models are trained to predict the next element, a discrete token or a continuous embedding, from the preceding context. Autoregressive prediction thereby provides a unified pre-training interface that transfers across modalities, compelling the model to learn the underlying data distribution. We ask whether such a simple causal paradigm can yield strong audio learners, given that audio's temporal structure makes autoregressive prediction of patch embeddings a natural fit. We introduce NAPE (Next-Audio-Patch-Embedding prediction), a self-supervised framework in which a causal Transformer predicts each next patch embedding of a log-mel spectrogram from the previous ones, using causal masking and stop-gradient as its sole training signal. The design is intentionally minimalist, avoiding reconstruction decoders, acoustic tokenizers, student-teacher setups, and auxiliary regularization losses. Across six audio and speech benchmarks, NAPE achieves state-of-the-art fine-tuning performance on several tasks, scales consistently across encoder sizes, and yields strong linear-probing results. NAPE also produces structured attention patterns without explicit supervision.
Read the full abstract

All authors Umberto Cappellazzo, Xubo Liu, Stavros Petridis, Maja Pantic

Audio and Speech Processing

DAVSS: Distilled Audio-Visual State Space Models

Saurabhchand Bhati, Mrudula Athi, Amit S. Chhetri et al. (+1 more)

State-space models (SSMs) distilled from transformer teachers combine the performance of transformers with the efficiency of SSMs. We extend the Transformer-SSM knowledge distillation to a multimodal setting and propose the Distilled Audio-visual State-Space (DAVSS) model. The DAVSS model, 14M parameters, is 12 times smaller compared to transformer-based models such as CAV-MAE, and still outperforms them. DAVSS improves over the existing audio-visual models by: 1) Finer input resolution: using smaller patch sizes process the input, compensating for the smaller model size by increasing input sequence lengths. This is supported by the observation that a larger patch size results in lower performance. 2) Deeper joint modeling: utilizing a larger portion of the model (30%) for joint audio-visual processing, compared to <5% in CAV-MAE, enabling deeper cross-modal interaction without significantly increasing the computational cost associated with the concatenated audio-visual tokens.
Read the full abstract

All authors Saurabhchand Bhati, Mrudula Athi, Amit S. Chhetri, James Glass

Wednesday 19 August

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

EMODY Flow: Emotion-Aware Audio-Driven Full-Body Motion Generation

Harsh Kumar Agarwal, Xavier Alameda-Pineda and Olivier Perrotin

Embodied conversational agents require synchronized full-body motion (body gestures and facial expressions) that aligns with speech and emotional state. Omni-modal large language models excel at multimodal understanding but produce only linguistic outputs, leaving a critical gap in embodied response generation. We identify and address a failure of emotion conditioning: like other conditional generators that under-use weak conditioning signals, a flow-matching model given both a rich audio embedding and a discrete emotion label suppresses the emotion, generating near-identical motion regardless of the specified emotion. We present EMODY Flow, a lightweight (around 35M parameters) flow-matching framework that attaches to a frozen Qwen-3 Omni model and reuses its internal Mimi audio-codecs to condition two parallel DiT generators - one for SMPL-X body pose, one for FLAME facial expressions. A training-time auxiliary emotion classifier restores emotion sensitivity by forcing generated motion to be emotion-identifiable. EMODY Flow sets a new state of the art on BEAT2 gesture quality, with FGD 0.302, Beat Correlation 0.853, and Diversity 24.62 - improving over the best prior results by 26%, 5%, and 62% respectively - and transfers to zero-shot facial animation on TFHP without domain-specific fine-tuning. Beyond these quantitative gains, the classifier yields clearly emotion-separated motion, which we demonstrate qualitatively through a multidimensional-scaling analysis of the generated gestures.
Read the full abstract

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

A Speech Corpus for Mizo Automatic Speech Recognition: Whisper and SraVaani 1.0 Fine-Tuning with Morphology-Aware Evaluation

Priyankoo Sarmah, Sanasam Ranbir Singh and Lalhmingmawia

This study reports the development of an Automatic Speech Recognition (ASR) system in Mizo, a low-resource language. The development included collecting 17.62 hours of speech data, curating it, and fine-tuning the Mizo ASR system with three Whisper multilingual models and with the SraVaani 1.0 Indic multilingual model. Whisper-large-v3 achieved the lowest conventional WER (18.08%), while morphology-aware evaluation yielded a WER of 7.22%. Zero-shot evaluation of the SraVaani 1.0 Indic multilingual model yielded a WER of 58.27%, while Mizo-specific fine-tuning reduced the conventional WER to 29.45% and the morphology-aware WER to 17.93%. The results demonstrate that the Whisper model can achieve a substantially low WER, even when adapted to an unseen language. In contrast, SraVaani 1.0 supports the Mizo language in its multilingual model; however, fine-tuning with carefully curated Mizo speech data substantially improves its performance.
Read the full abstract

Tuesday 18 August

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

Low-Power, Neuromorphic, Acoustic Anomaly Detection for Persistent Machine Monitoring

Steven C. Nesbit, Victor M. Vergara, Michael A. Felix et al. (+4 more)

Persistent acoustic monitoring can detect machine faults without physical contact, but always-on inference is constrained by power, latency, and deployment complexity. We demonstrate autoencoder-based acoustic anomaly detection on an Intel Loihi 2 neuromorphic processor under clean and noisy conditions. Log-mel features are computed off chip; normalization, autoencoder inference, L1 reconstruction scoring, and thresholding run on chip. In a clean, microphone-position-invariant ToyADMOS ToyCar benchmark, the on-chip model achieves 0.9959 AUC and 0.9785 standardized pAUC at maximum false-positive rate 0.1. In the DCASE 2026 Task 2 ToyCar noisy benchmark, the model achieves source AUC 0.7990, target AUC 0.6466, and pAUC 0.6426, exceeding reported baseline metrics. Power profiling on a 16-chip Loihi 2 VPX system shows real-time throughput with 0.0406$\unicode{x2013}$0.0426 mJ dynamic energy per sample, two orders of magnitude lower than both a CPU and GPU. These results support neuromorphic acoustic anomaly detection as a practical candidate for low-power, persistent machine monitoring.
Read the full abstract

All authors Steven C. Nesbit, Victor M. Vergara, Michael A. Felix, Evan T. Kain, Luis R. García Carrillo, Gerd J. Kunde, Andrew T. Sornborger

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

ChiroEcho: extending automated bat vocalisation classification beyond the learned taxonomy

Burooj Ghani, Welmoed Eversteijn, Milan van Hirtum et al. (+4 more)

Bats are key indicators of ecosystem health and are protected throughout Europe, making reliable population monitoring a conservation priority. Their cryptic nocturnal lifestyle makes passive acoustic monitoring essential, yet automated identification remains difficult as echolocation calls vary with behaviour and environment and overlap among species. We present a deep learning framework that jointly predicts species and genus and combines genus predictions with geographic species distributions at inference. When only one species of a predicted genus occurs in a region, the framework can resolve species absent from the learned taxonomy. This reframes geographic information as a means of extending, rather than constraining, a classifier's effective taxonomy. Using recordings spanning 35 European bat species, we evaluate closed-set classification, examine the instability of performance estimates for sparsely represented species, and conduct a controlled held-out proof-of-principle experiment. The rare-species analysis shows how limited evaluation data can obscure species-level performance, while the held-out experiment shows that genus predictions and location can recover labels unavailable to the species head. Geographic resolution extends operational coverage from 35 to 41 of the 48 native European bat species, increasing coverage from 73% to 85%. To our knowledge, this is the broadest operational coverage reported for automated European bat classification. More broadly, the bat framework provides proof of principle for resolving unseen fine-grained classes by combining coarse predictions with transparent external constraints.
Read the full abstract

All authors Burooj Ghani, Welmoed Eversteijn, Milan van Hirtum, Juan Sebastián Cañas, Vincent J. Kalkman, Dan Stowell, A. Leonie Baier

Audio and Speech Processing

DNN-Based Frequency-Dependent Estimation of Speech, Music, and Noise Power in Acoustic Mixtures for Hearing-Aid Scene Analysis

Mats Lang, Thomas Haubner, Nina Kiessling et al. (+2 more)

Acoustic scene analysis is essential for adapting hearing-aid signal processing algorithms to the current listening environment. However, state-of-the-art (SOTA) systems typically rely on multiple independent estimators for tasks such as scene classification, Voice Activity Detection (VAD), or Signal-to-Noise Ratio estimation, which increases computational complexity and fails to exploit dependencies between related tasks. To address this problem, we propose a unified and interpretable acoustic scene representation by decomposing the observed mixture spectrum into speech, music, and noise power components. This is motivated by the typical listening targets of hearing-aid users. In particular, we estimate time- and frequency-dependent power proportions by a causal low-complexity Deep Neural Network, from which multiple downstream acoustic scene analysis measures can in principle be derived by simple post-processing. In this work, we validate the proposed representation using VAD as a representative downstream task and show performance comparable to a SOTA estimator while providing a substantially richer scene description.
Read the full abstract

All authors Mats Lang, Thomas Haubner, Nina Kiessling, Christoph Hoog Antink, Henning Puder

Monday 17 August

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

A Multiplication-Free Feature Extractor for Signal Classification: Keyword Spotting Case Study

Radu Dogaru and Ioana Dogaru

A very low complexity feature extractor called next iRDT is proposed and evaluated for the problem of keyword spotting (KWS). Unlike any other types of feature extractors including the widely used MFCC, or adaptive, CNN-based ones, our algorithm is multiplier-free and it employs only simple, energy-efficient arithmetic operators. Since keyword-spotting of speech commands (KWS) is a typical application for TinyML platforms requiring low complexity for the signal classification chain, we consider it as a case study to evaluate complexity and functional performance. If properly tuned, iRDT demonstrates similar accuracy to solutions based on MFCC or CNN-based extractors using baseline classifiers on Google's KWS 12-classes dataset. With a different classifier the system achieved 94.7% validation accuracy. Processing times on CPU for the proposed feature extractor, are at least one order of magnitude smaller than for the MFCC. The proposed algorithm has a very low hardware footprint, making it ideal for ultra-low power edge devices. Code and demo are available [18].
Read the full abstract

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

Emotion Across Speech and Faces: Shared Affective Mechanisms in Multimodal Foundation Models

Xiutian Zhao, Luqi Sun, Björn Schuller et al. (+1 more)

Modern multimodal foundation models (MFMs) have made rapid progress on tasks requiring integrated perception across speech, vision, and language, including emotion recognition. However, it remains unclear whether they recognize speech and facial emotion through shared affective functional units or modality-specific pathways. We explore emotion-sensitive neurons (ESNs), sparse decoder neurons selectively associated with emotion categories, in three MFMs: Gemma-4-12B-it, MiniCPM-o-4.5, and Qwen2.5-Omni-7B. Using speech emotion recognition and facial expression recognition as complementary probes, we identify acoustic and visual ESNs. Visual ESNs are causally meaningful: deactivating them selectively impairs recognition of the associated facial emotion, whereas steering their activations selectively enhances recognition of that emotion relative to other emotion categories. Acoustic and visual ESNs further show emotion-matched overlap and similar layer-wise distributions, indicating partial structural alignment between affective representations across speech and faces. Finally, cross-modal interventions reveal bidirectional causal transfer: ESNs identified from one modality produce emotion-specific effects when applied to the other. Our findings provide one of the first cross-modality activation-level analyses of affective functional units in MFMs, suggesting that speech and facial emotion recognition partially converge onto sparse decoder-level components that can be localized and manipulated without training.
Read the full abstract

All authors Xiutian Zhao, Luqi Sun, Björn Schuller, Berrak Sisman

Audio and Speech Processing

Numerical and perceptual validity of synthetic Head-Related Transfer Functions at scale

Katarina C. Poole and Lorenzo Picinali

Individually measuring head-related transfer functions (HRTFs) at scale remains a central challenge for personalised spatial audio, motivating growing interest in synthetic HRTFs. We evaluated the numerical, computational, and behavioural validity of synthetic HRTFs, generated through the boundary element method simulation using Mesh2HRTF, against measured and KEMAR HRTFs using the Extended SONICOM dataset. Across 200 subjects, synthetic HRTFs deviated less from measured than KEMAR in interaural time and level differences, but residual errors, together with elevated spectral distortion, concentrated at low, rear elevations. This is consistent with the omission of torso geometry from the synthesis pipeline. Two computational models revealed a corresponding pattern of predicted localisation errors, with synthetic HRTFs positioned between measured and KEMAR. In a virtual reality localisation task (N = 20), synthetic HRTFs matched measured on every polar metric, while KEMAR was significantly worse. However, behavioural error clustered around the front-back midline regardless of condition, not at the low elevations implicated numerically or by the models. A separate spatial release from masking task (N = 18) showed no effect of HRTF type. Together, these results indicate that high-resolution synthetic HRTFs preserve behavioural localisation performance, despite discrepancies between the numerical/model-predicted bias and the spatial pattern of behavioural error.
Read the full abstract

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

Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization

Tony Alex, Wish Suharitdamrong, Sara Atito et al. (+5 more)

Large Audio Language Models (LALMs) have made rapid progress on standardized benchmarks, yet their deployment in practical media workflows, curation, archival indexing, and content distribution remains largely unrealized. We identify automated audio chapterization, the task of segmenting continuous audio streams into thematically coherent chapters, as a demanding and commercially consequential setting that exposes this gap. Chapterization is challenging because boundaries are defined less by objective acoustic events than by subjective editorial judgment, requiring models to reason sequentially over long acoustic contexts and approximate creator-authored boundary decisions. We present AudioChaps, a post-training framework for aligning end-to-end LALMs for this task via Group Relative Policy Optimization (GRPO) guided by Chain-of-Thought (CoT) reasoning. To support training and evaluation, we curate three datasets: AudioChaps-Alignment, derived from creator-annotated chapter boundaries on YouTube; AudioChaps-CoT, which provides structured supervision for well-formatted, high-quality, and evidence-grounded boundary reasoning; and AudioChaps-Eval, a held-out benchmark for audio chapterization. Applying GRPO directly without a Supervised Fine-Tuning (SFT) cold start, AudioChaps-R1-Zero already improves average F1 by 33 points over the state-of-the-art LALM Audio-Flamingo-3-Think. The AudioChaps framework produces our final aligned LALM, AudioChaps-R1, which improves average F1 by 49 points. These results demonstrate that GRPO-trained LALMs can reliably transform unstructured auditory streams into navigable, structured media. Our code, models, and dataset resources will be released upon acceptance at https://github.com/ta012/AudioChaps.
Read the full abstract

All authors Tony Alex, Wish Suharitdamrong, Sara Atito, Armin Mustafa, Muhammad Awais, Philip J. B. Jackson, Jiankang Deng, Ismail Elezi

Audio and Speech Processing

Sonifying I2S Transport Signals to Detect Transmission Faults

Stephen Roddy

This paper outlines a sonification design to support fault detection in the transmission of I2S transport signals. I2S is a protocol for communicating real-time digital audio between integrated circuits that, while in wide and general use, does not include built-in error detection. Moreover, given the nature of the protocol transmission faults affecting timing, framing and alignment can be difficult to identify using conventional visual methods. The proposed design addresses this with an approach informed by Audification, wherein oversampling controls temporal rescaling to render protocol structure (SCK and WS) and payload data (SD) across separate stereo channels. A preliminary computational feasibility study was carried out to measure feature-space separability of I2S faults in the generated auditory representations as opposed to listener performance. It evaluates the design across several payload types and error conditions including jitter, bit-slip, and word-length errors. Class separability was assessed through clustering analyses of extracted features. The evaluation results show that while oversampling produces systematic changes in feature values, it does not meaningfully improve separability between error classes. However, a modest but consistent improvement in separability is observed as a function of the joint representation of structural and payload information across channels. The findings suggest that feature-space separability in sonified communication protocol data may be dependent on the integration of complementary information streams, rather than on signal scaling alone.
Read the full abstract