Peer Revenue Publish or profit

Papers

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

Computer Science Sound

cs.SD Watch Sound

Monday 14 September

Sound

Cross-Lingual F5-TTS 2: A Simplified Framework for Language-Agnostic Voice Cloning

Qingyu Liu, Rixi Xu, Yushen Chen et al. (+11 more)

Zero-shot text-to-speech (TTS) can clone a speaker's voice from a short audio prompt, yet most TTS systems still require the audio prompt transcript during inference. This dependency prevents cross-lingual voice cloning when the audio prompt transcript is unavailable, particularly for unseen languages. Cross-Lingual F5-TTS removes this dependency and enables transcript-free cross-lingual voice cloning, but it prepares its training data with forced alignment. Forced alignment is sensitive to boundary errors, and its cost grows as more languages are covered. Its speaking rate predictor is also unreliable at estimating duration when the audio prompt begins or ends with silence. In this paper, we present Cross-Lingual F5-TTS 2, a simplified framework for transcript-free cross-lingual voice cloning without forced alignment. Instead of using forced alignment to segment real utterances, we build same-speaker prompt and target pairs using a pretrained F5-TTS model and fine-tune the same model on these constructed pairs. This simplifies data preparation and preserves the acoustic modeling capability of the pretrained model, enabling adaptation with only a short fine-tuning stage. We further make the syllable-level speaking rate predictor robust to leading and trailing silence through silence-aware augmentation. Experiments show that Cross-Lingual F5-TTS 2 reaches higher speaker similarity than F5-TTS and Cross-Lingual F5-TTS while maintaining intelligibility. All related resources are publicly available.
Read the full abstract

All authors Qingyu Liu, Rixi Xu, Yushen Chen, Zhikang Niu, Haitao Li, Pengcheng Zhu, Bowen Zhang, Jian Zhao, Yunting Yang, Qinyuan Cheng, Xipeng Qiu, Berrak Sisman, Kai Yu, Xie Chen

Sound

Rethinking Procedural Audio Pre-training: Source Scaling and Objective Adaptation

Jiajun Peng, Fengrui Liu, Xinyu Liu et al. (+1 more)

Procedural audio has emerged as a viable source for transferable audio representation learning, but its design principles remain unclear.We revisit two questions: how a procedural source should be scaled, and whether training choices developed on natural audio should transfer unchanged to procedural data.Using a controlled source, we separate scale into formula-class coverage C and within-class rendering diversity I.Experiments with FDSL and AudioMAE show that these two forms of scale provide different benefits and depend on the learning formulation and downstream task. A matched AudioMAE study further shows that procedural audio favors low mask ratios (10%–25%), whereas AudioSet-28K favors 50%–75%. Shared-codebook analysis reveals lower patch diversity and stronger temporal predictability in procedural audio. These results motivate source-aware procedural pre-training, where source scaling and learning configuration are considered jointly.Code is available at https://github.com/Cross-Innovation-Lab/Formula-Bank.
Read the full abstract

All authors Jiajun Peng, Fengrui Liu, Xinyu Liu, Feng Liu

Sound · Cross-listed from cs.CL

Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow Fusion

Warit Sirichotedumrong, Tanawin Samutsin, Shah Faisal Wani et al. (+2 more)

Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling out low-latency uses such as live captioning and voice agents. We present a deployable system for streaming Thai ASR that lets a user steer its vocabulary at decode time, without retraining. A widely used open Thai model, trained with full context, collapses when run as a true stream; we restore streaming with a cache-aware encoder, by converting it or adapting a natively streaming one, and add a shallow-fusion layer that re-ranks candidates inside the streaming decoder with a GPU n-gram language model and phrase boosting. Across two Thai benchmarks and two model sizes, the streaming models stay usable where the full-context model fails, cutting character error rate 4.3-4.5x at a one-second look-ahead while running faster than real time. Decode-time steering then lifts keyword recall from 16.6% to 20.7% at no accuracy cost and negligible overhead; most of the gain comes from an n-gram over ordinary training transcripts, which resolves the written form of code-switched words the model hears but spells inconsistently, with phrase boosting adding targeted control over rare domain terms.
Read the full abstract

All authors Warit Sirichotedumrong, Tanawin Samutsin, Shah Faisal Wani, Sittipong Sripaisarnmongkol, Kunat Pipatanakul

Sound · Cross-listed from eess.AS

Learned Bow Control on a Measured Bowed-String Model: a Revised Minimum-Bow-Force Law, a Recurrent Controller, and the Domain of a Supervision Ceiling

Homayoon Beigi and Grace Conneely

A finite-difference bowed-string model with implicitly resolved Stribeck friction is presented, with a regime diagnostic. Without implicit resolution no stick phase forms at any bow force. With friction, impedance and quality factor from published measurement rather than fitted, all four strings return a stick fraction of 89.1% against an ideal 90%. Schelleng's maximum bow force is recovered on every string. His minimum, $F_{\min} \propto Z^2 v_b \beta^{-2}$, is replaced by a law, $F_{\min} = C Z v_b / \beta$ with a dimensionless $C = 1.112 \pm 0.017$ that reproduces on sixty-four held-out operating points. Six controllers at matched capacity, on four strings at twenty seeds, place a gated recurrent network ahead of a feedforward one, its margin over the mean of the other five largest when the commanded bow speed is overridden at mid-stroke. The feedforward network completes more strokes, mostly from a cold start no player would use. A minimal gated variant fails because gates computed from the input alone cannot clear a latched state. Training loss selects neither the capacity nor the context length. No learned controller improves on the lookup rule that generated its labels where that rule is correct. Of the rule's 1089 cells, 57 are playable on a properly settled plant and unplayable by its labels, and the controller commands them where the lookup will not. The controller's score regresses on the rule's with a slope of 0.32, more than ten standard errors below unity, so it overtakes the rule where the rule fails and is bounded by it where it holds. Under a rigid finger stop the plant is provably invariant, so transfer loss between pitches is the controller's alone, traced to one feature. A regime classifier without a stick test mistakes small-amplitude periodic slipping for Helmholtz motion, and a harmonicity measure rates a string the bow never grips above it.
Read the full abstract

Sound

CAL-MOS: Bridging Layers with Adapters for Robust MOS Prediction Across Speech Foundation Models

Alef Iury Siqueira Ferreira, Pedro Lustosa Rege Botelho, Fernanda Silva et al. (+5 more)

Speech Quality Assessment (SQA) is essential for modern speech technologies, and recent non-intrusive SQA predictors increasingly rely on Speech Foundation Models (SFMs). However, because SFMs expose representations from many layers, it remains unclear which depths are most informative for MOS prediction and how multi-layer information should be combined reliably across backbones and datasets. We benchmark ten SFMs on four MOS datasets under three regimes: full fine-tuning, last-layer probing with a frozen encoder, and naive cross-layer weighted aggregation. We find that the best layer is strongly backbone- and dataset-dependent, and that naive weighted fusion can be unstable across settings. We further evaluate a layer-calibrated aggregation variant that applies per-layer adapters before pooling, which improves the robustness of multi-layer fusion and narrows the gap to full fine-tuning while keeping the backbone frozen.
Read the full abstract

All authors Alef Iury Siqueira Ferreira, Pedro Lustosa Rege Botelho, Fernanda Silva, Daniel Casanova, Rafael Faustino, Frederico Oliveira, Arlindo Galvão Filho, Anderson da Silva Soares

Sound

Tracing the Origins: Legacy Codec Identification in Neural Audio Transcoding

Wonje Heo, Shinee Youn, Yooshin Kim et al. (+2 more)

Residual Vector Quantization (RVQ)-based neural audio codecs (NACs) enable high-fidelity audio distribution at unprecedentedly low bitrates through discrete token-based representations. However, this shift disrupts traditional forensics, as non-linear neural transcoding obscures the underlying traces of legacy compression. This study defines the forensic gap and proposes a Transformer-based framework designed to leverage the hierarchical and temporal dependencies inherent in RVQ sequences. By modeling inter-layer causal relationships and dynamic forensic significance, our model effectively disentangles superimposed artifacts from legacy-to-neural transcoding. Experimental results achieve 97%+ accuracy for codec identification and robust joint identification performance across 32-128 kbps. These results demonstrate that traditional codec traces persist even after neural transcoding, supporting the feasibility and necessity of neural-codec-aware audio forensics.
Read the full abstract

All authors Wonje Heo, Shinee Youn, Yooshin Kim, Chuck Chae, Donghoon Shin

Sunday 13 September

Sound

POLARIS: Training-Free Audio Fingerprinting with Saliency-Based Landmarks and Delaunay Grouping

Jiheng Li

This work presents POLARIS, a training-free audio fingerprinting system that selects landmarks from a locally normalized saliency field and groups them into sparse fingerprints using Delaunay triangulation. To deal with query distortion, POLARIS adds fingerprints from two-hop Delaunay neighborhoods only at query time, without enlarging the reference index. An adaptive configuration applies this expansion only when the original fingerprints do not produce a confident match. We evaluate POLARIS on synthetic distortions from the public PEX Hard Medium benchmark, excluding queries with pitch or tempo shifts, and on a new benchmark of real re-recorded music. POLARIS achieves the best performance among the evaluated training-free methods on both benchmarks. On the real recordings, its adaptive configuration also outperforms the neural NMFP baseline with a comparable measured query time and a smaller logical reference payload. Code, dataset, and instructions for reproducing all experiments are available at https://github.com/JihengLi/POLARIS.git.
Read the full abstract

Sound

CCMAN: Cognitive Instability-Aware Cross-Modal Attention Network for Interpretable Temporal Biomarkers of Verbal Fluency Speech

Madhurananda Pahar, Caitlin Illingworth, Dorota Braun et al. (+2 more)

Early detection of cognitive decline from speech offers a scalable and non-invasive alternative to conventional clinical assessment. Verbal fluency tasks are particularly informative, but most automated approaches aggregate features across an entire recording, overlooking temporal speech dynamics. We propose the Cognitive Instability-Aware Cross-Modal Attention Network (CCMAN), a transfer learning framework that learns task-agnostic cognitive speech representations from multiple memory-probing tasks before fine-tuning on a minute-long semantic and phonemic verbal fluency task. CCMAN integrates semantic, acoustic, and linguistic information through bidirectional cross-attention, gated multimodal fusion, and transformer-based temporal modelling to derive interpretable biomarkers of cognitive decline. Experiments were conducted on 165.44 hours of speech from 843 participants (498 healthy controls, 245 with mild cognitive impairment, and 100 with dementia). CCMAN achieved Macro-F1 scores of 0.81 and 0.59 for binary and multiclass semantic fluency classification, and 0.77 and 0.53 for phonemic fluency, consistently outperforming strong static and temporal baselines. Statistical analyses showed that semantic drift variance and pause variance, but not mean semantic drift, were significantly elevated in both MCI and dementia relative to healthy controls, while pause duration increased progressively over the task with the steepest slope in dementia, supporting global and progressive temporal speech instability as interpretable biomarkers. Evaluation on the independent PROCESS-2 benchmark further demonstrated the generalisability of the proposed framework, improving the baseline Macro-F1 by up to 9%. These findings support temporal speech instability as a dynamic speech biomarker for robust, interpretable, and generalisable early detection of cognitive decline.
Read the full abstract

All authors Madhurananda Pahar, Caitlin Illingworth, Dorota Braun, Daniel Blackburn, Heidi Christensen

Sound · Cross-listed from eess.AS

Bridging Data, Reasoning, and Alignment: A Unified Framework for Context-Aware Instruction-Following TTS

Jingbin Hu, Luyu Wang, Wenjie Tian et al. (+7 more)

The ISCSLP 2026 CoT-TTS Challenge requires TTS systems to generate Chain-of-Thought (CoT) reasoning from dialogue history before synthesizing contextually appropriate speech. While the official baseline establishes a unified architecture, it remains constrained by limited contextual comprehension, weak instruction fidelity, and suboptimal audio quality. We present a systematic optimization pipeline to address these limitations. First, we develop a data process framework that cleans raw data via FullSubNet denoising, Qwen3-ASR re-transcription, and Qwen3.5-35B-A3B-based history-CoT consistency analysis, while distilling 545K high-fidelity instruction samples using Qwen3-TTS and Seed-VC under strict quality filtration. Second, we propose a Context-Aware Direct Preference Optimization (CA-DPO) method. By employing a cascaded filtering strategy, ASR prescreening, LLM tournament ranking, and speaker similarity verification, we obtain high-confidence preference pairs that significantly enhance holistic “Context$\rightarrow$CoT$\rightarrow$Speech” consistency during DPO training. Third, we establish an evaluation method featuring a 500-sample test set and an LLM-as-Judge framework to independently assess reasoning and execution fidelity. Experiments demonstrate that our system significantly outperforms the baseline across all objective and subjective metrics, validating our data governance and alignment strategies.
Read the full abstract

All authors Jingbin Hu, Luyu Wang, Wenjie Tian, Kangxiang Xia, Qirui Zhan, Haoyu Zhang, Yunxiang Chen, Houdun Liu, Lei Xie, Liumeng Xue

Sound · Cross-listed from eess.AS

Parameter isolation with domain-specific experts for incremental audio classification

Jongyeon Park, Do-Hyeon Lim, Sang-won Park et al. (+4 more)

To successfully deploy a model in time-varying environments such as streaming data prediction and sensing control, domain-incremental learning (DIL) has attracted attention since it aims to adapt a previously trained model to newly arriving domains, while reserving knowledge from earlier domains without accessing their data. Incremental learning across domains can be regarded as a recurrent update, in which the current model is obtained by updating the model carried over from previous domains. Conventional DIL approaches that rely on domain-invariant feature learning and weight regularization gradually overwrite or constrain parameters learned in previous domains, leading to catastrophic forgetting. Instead, this paper proposes a new domain-specific parameter-isolation architecture that retains all past domains. The proposed architecture mitigates catastrophic forgetting through a full-order recurrent update, constructing a new expert using domain-specific data conditioned on all previously frozen models. To achieve this, we incorporate data-free generative replay to reconstruct previous-domain data and cross-domain feature generation to recover later expert features missing from earlier domain samples. Finally, we apply the proposed model architecture to domain-agnostic incremental learning for audio classification, as defined in the DCASE 2026 Challenge Task 7. Consequently, we achieve micro and macro accuracies of 78.4% and 78.9%, respectively, representing increases of 33 and 25 percentage points over the Challenge baseline. Ablation studies are conducted to examine the effectiveness of each processing component in terms of classification accuracy.
Read the full abstract

All authors Jongyeon Park, Do-Hyeon Lim, Sang-won Park, Hong Kook Kim, Kyungdeuk Ko, Hyeongcheol Geum, Jeong Eun Lim

Sound · Cross-listed from eess.AS

Exploring Multimodal Turn-Taking Cues in Face-to-Face Conversation using Voice Activity Projection

Willem Berner, Julio Cesar Cavalcanti, Kalle Åström et al. (+1 more)

Turn-taking is a fundamental component of spoken interaction, and while humans naturally rely on both verbal and non-verbal signals, dialogue systems usually depend on audio cues alone. This paper investigates whether visual features from face-to-face conversations can enhance turn-taking prediction beyond what is achievable from audio-only. We extend the Voice Activity Projection (VAP) model, a self-supervised transformer-based model for predicting future voice activity, by incorporating visual features extracted from the large-scale Meta Seamless Interaction dataset of dyadic face-to-face conversations. The visual features include gaze direction, head movement, body and hand pose, and facial action units (FAU). For incorporating the visual features, we explore concatenation, cross-attention fusion, delta features, and trainable gating mechanisms. Results show that visual information improves performance over the audio-only baseline, with FAU being significantly more informative than other feature groups. Body and gaze features nevertheless contribute complementary information, as the model combining all features performs best. Furthermore, results indicate that performance on specific tasks varies depending on whether training and test data come from improvised (acted) or naturalistic (non-acted) conversations.
Read the full abstract

All authors Willem Berner, Julio Cesar Cavalcanti, Kalle Åström, Gabriel Skantze

Sound · Cross-listed from cs.CL

Neyshekar: An Open Persian Read-Speech Corpus for Automatic Speech Recognition

Ahmad Amirivojdan, Farzad Nadiri, Abolfazl Alizadeh et al. (+1 more)

Neyshekar is presented as an open Persian read-speech corpus designed for coverage of both formal and informal language, named entities, and longer utterances. In version 6, 62,279 validated recordings totalling 99.02 hours are provided from 190 contributors, with 34,541 distinct recorded prompts. The prompt pool was assembled from human-written material, contextualised homographs, and reviewed language-model-generated text. Text entries were normalised with the shekar library, which supports both formal and informal Persian, and every submitted recording was reviewed against a common validation rubric. About 24% of released clips are classified as informal by an automatic classifier; these register labels are not human-validated. Item-level rater labels are provided for reproducible agreement estimation, opaque per-clip contributor identifiers make the speaker-disjoint partitioning auditable and support contributor-clustered uncertainty estimates, and a text-disjoint test subset is included for evaluation beyond previously seen prompts. Per-contributor recording load and reference-free signal quality are characterised for every released clip. Corpus characteristics are compared with Persian Common Voice under shared processing. Utility is assessed through two ASR architectures, three optimisation seeds, WER and CER, and independent evaluation on the public PSRB sample. Against duration-matched Common Voice training at approximately 32 hours, in-domain WER is reduced by 9.5 points for Whisper and 11.6 points for XLS-R, and by approximately eight points for both architectures on the independent PSRB sample. Transfer and mixture benefits are not consistently observed across architectures and training budgets. The corpus is released under CC0; code and data are made available through the project repository at https://github.com/amirivojdan/neyshekar.
Read the full abstract

All authors Ahmad Amirivojdan, Farzad Nadiri, Abolfazl Alizadeh, Shaghayegh Yaraghi

Sound

Bridging the Modality Gap in Long-Form Clinical Audio: A Comparative Study of Lightweight and Heavyweight End-to-End SOAP Generation

Ziyu Zhang, Mingchen Shao, Wenjie Tian et al. (+3 more)

Automating clinical documentation from long-form doctor-patient conversations remains challenging for modern audio-language models. While cascaded ASR systems perform well, end-to-end (E2E) models often struggle with information loss and hallucinations on extended audio. For the BeTraC 2026 challenge, the ASLP team presents a fully E2E multimodal system that generates structured SOAP notes directly from audio, bypassing intermediate transcripts. We constructed a 1.41-million-sample multi-task corpus and applied a multi-stage pipeline: domain pre-training, supervised fine-tuning, and reward optimization. Evaluating the architecture under both Lightweight (3B) and Heavyweight (30B) constraints reveals that each training stage progressively enhances performance. Furthermore, scaling to 30B parameters substantially boosts concept extraction and summarization quality. Ultimately, our E2E systems consistently outperform representative cascaded ASR+LLM baselines, proving the efficacy of direct multimodal optimization for clinical documentation.
Read the full abstract

All authors Ziyu Zhang, Mingchen Shao, Wenjie Tian, Tianlun Zuo, Longhao Li, Lei Xie

Sound

Grounded in Sound: Reinforcement Learning with a Frozen Acoustic Judge to Curb ASR Insertion Hallucinations

Tingzhen Xiong, Rilin Chen, Weiwei Li et al. (+2 more)

When reinforcement learning (RL) is used for post-training automatic speech recognition (ASR), the reward almost always lives in the text space: it compares a hypothesis with the reference and never checks whether the hypothesis is supported by the audio. On highly regular speech this licenses a shortcut - guessing from a strong language prior rather than listening. Once the acoustics degrade, the shortcut runs unchecked and emits fluent but ungrounded words, i.e., insertion errors. We propose an acoustic-fidelity reward: a GRPO reward augmented with a separately pretrained, permanently frozen, non-autoregressive character-level wav2vec2-CTC acoustic judge, used strictly at training and absent at inference, where a single model decodes greedily. Trained on LibriSpeech and evaluated across a six-tier difficulty gradient including real AMI meeting speech (33,282 utterance-condition instances), the method reduces insertion errors by 28.3% on close-talking AMI-IHM and 22.3% on far-field AMI-SDM, while lowering WER on AMI-SDM from 35.89% to 34.71% and showing no detectable WER difference on the other five tiers, against a schedule-matched WER-GRPO baseline. The insertion reduction holds under a meeting-level clustered bootstrap. Four prespecified analyses support content-conditioned insertion calibration: output collapses 85-90% on unintelligible audio that preserves energy and voice activity; the gain is not recovered by the evaluated 32-best CTC rescoring configuration, yet RL internalizes it into a single greedy decoding run; and policy-only confidence yields lower insertion-AURC in all four evaluated settings. We frame this as a mechanism paper, demonstrated in one instantiation: a 7B speech LLM with a 0.3B CTC judge.
Read the full abstract

All authors Tingzhen Xiong, Rilin Chen, Weiwei Li, Wentao Zhang, Qicong Xie

Sound

Exploiting Speech LLM Representations for Multilingual and Cross-Lingual Parkinson's Disease Detection

Sarthak Giri, Zi Haur Pang and Tatsuya Kawahara

Speech Large Language Models (Speech LLMs) have shown strong performance across diverse tasks, yet their utility for pathological speech analysis remains underexplored. In this work, we investigate the effectiveness of internal representations from encoder and decoder components of Speech LLMs for Parkinson's Disease (PD) detection across multilingual and cross-lingual settings. Our findings reveal that encoder representations consistently outperform their decoder counterparts in most models and settings and that pathological cues may be progressively attenuated as audio representations are projected into the language model space. We further show that generative outputs are less reliable for clinical tasks compared to internal representations. To leverage information spread across multiple layers, we propose a Squeeze-and-Excitation (SE)-based dynamic layer aggregation framework, which surpasses best-layer selection in multiple experiments, suggesting that PD-relevant acoustic cues are distributed across transformer layers rather than concentrated in one.
Read the full abstract

Sound

Differentiable Digital Signal Processing Mixture Model-Guided Diffusion for Synthesis Parameter Estimation from Harmonic Sound Mixtures

Kengo Takemoto, Tomohiko Nakamura and Hiroshi Saruwatari

A differentiable digital signal processing (DDSP) autoencoder reconstructs a monophonic harmonic sound through three types of synthesis parameters: fundamental frequency, loudness, and timbre features. To handle mixtures of harmonic sounds within the DDSP approach, we have previously proposed a DDSP mixture model (DDSPMM). It represents a mixture as the sum of source signals synthesized by the decoders of pretrained DDSP autoencoders. Although DDSPMM enables direct estimation of synthesis parameters of each source from mixtures, it does not explicitly model temporal variations in the synthesis parameters and can produce excessive temporal fluctuations. In this paper, we propose a method for estimating synthesis parameters with temporally plausible trajectories by incorporating a denoising diffusion probabilistic model (DDPM) into the DDSPMM-based estimation. The DDPM is trained as a generative model of synthesis parameters. During estimation, the proposed method guides the DDPM reverse diffusion process with the reconstruction error between the observed mixture and the mixture synthesized by DDSPMM from the current estimates. Experiments on woodwind and string instrument ensembles showed that the DDPM-based regularization improves synthesis parameter estimation by imposing temporal plausibility on the estimated trajectories.
Read the full abstract

Sound

AURA: Unified Multimodal Framework for Conversational Music Editing

Quoc-Huy Trinh, Minh-Van Nguyen and Debesh Jha

Instruction-guided music editors typically process each request independently, limiting their ability to support workflows in which users progressively refine a track. We introduce AURA, a unified multimodal framework for conversational music editing. AURA uses a multimodal large language model to interpret the complete dialogue history, an optional image, and reference audio, distilling the editing intent into compact concept tokens. A concept-to-audio module injects these tokens and frame-aligned reference features into a frozen MusicGen backbone, enabling precise edits while preserving unaffected content. AURA optimizes only 91M parameters while retaining 1.9B frozen backbone parameters. Experiments on Slakh2100 and MoisesDB demonstrate substantial improvements in edit correctness and content preservation over existing instruction-guided methods, including a 4-5 times reduction in FAD for out-of-domain addition and removal.
Read the full abstract

Saturday 12 September

Sound · Cross-listed from cs.LG

Inherited Heads: Audio language models track speakers with their text backbone's attention, and an attention-mass ranking retrieves a different set

Bojro Das

Asked to describe what one of six speakers in a recording talks about, audio language models describe the right one on 6 to 16% of trials, below the 16.7% a guess would give. Adding a fixed bias to the attention logits of a hundred heads, under a tenth of the model's and with no training, redirects the description to whichever speaker we choose, on 90.7% to 99.0% of trials. Those heads are largely not specific to audio. Rank the text-only language model an audio model was built from, or a released model of the same family, on a written version of the task, take its top hundred heads, and carry them over unchanged: they redirect the audio model on 80.8% to 95.0% of trials, with nothing about audio entering the selection. The audio and text head sets share 66 to 74 of 100 where chance would give about 20, and the shared part alone reproduces almost all of the steering. What that does not show is that sharing is what makes the heads work: an equal-sized draw from the same discovered hundred does nearly as well, and none of our three models separates the two explanations. A second finding concerns how such heads are found. Ranking heads by how much attention they place on the segment asked about, as an established score does, or by how much of their attention moves with the question, as a per-head normalised variant does, gives top hundreds that share 69, 37 and 4 heads across our three models. In Ultravox, where they share 4, the established score's heads leave output the judge cannot place on any segment on 69.7% of trials, against 40.0% with no intervention and 1.0% for the normalised variant. That is one arm of six; on the other five the established score steers above a random draw.
Read the full abstract

Sound

A New Transformer-Based Approach for Audio-Based Kinship Verification and a New Uncontrolled Mandarin Kinship Speech Dataset

Qiyang Sun, Langqing Zhang, Yupei Li et al. (+1 more)

Kinship verification is a task involving determining whether two individuals share a first-order kin relation. To tackle this task, we propose CONVTRAP-TN, a new architecture for audio-based kinship verification, and conduct an ablation study on the proposed model. To the best of our knowledge, we are the first to apply the successful transformer architecture to the task of audio-based kinship verification. Furthermore, we also collect a custom speech dataset, ARKIN, which accurately reflects everyday recording conditions. We do this because only a few speech datasets with kinship labels currently exist, all of which either source extremely noisy in-the-wild data from the internet, or instruct speakers to record in specific environments. These settings fail to reflect real-world scenarios where users record on personal devices under unrestrained conditions. Additionally, we perform a series of preliminary baseline experiments on the collected dataset, including speaker verification and recognition, speech recognition, age estimation, and kinship verification, as well as cross-dataset kinship verification experiments to show that existing methods are not robust across datasets.
Read the full abstract

All authors Qiyang Sun, Langqing Zhang, Yupei Li, Björn Schuller

Sound

Robust Cross-Domain Speech-Based Alzheimer's Disease Detection via Iterative Adversarial Self-Training

Luqi Sun, Shreeram Suresh Chandra, Aurosweta Mahapatra et al. (+3 more)

As Alzheimer's disease (AD) has increasingly become a major global public health issue, speech-based AD detection has attracted widespread attention. However, most existing methods are trained and evaluated on a single dataset, often leading to severe cross-domain performance degradation due to reliance on dataset-specific artifacts rather than disease-related speech cues. In real-world applications, reliable Alzheimer's disease detection requires models that are robust to variations in recording environments, speakers and data collection conditions. To address this challenge, this paper adopts unsupervised domain adaptation to learn robust, domain-invariant feature representations in the absence of target-domain diagnosis labels. On this basis, a novel unsupervised domain adaptation method, Iterative Adversarial Self-Training (IAST), is proposed. Results demonstrate that IAST significantly improves the generalization ability and robustness under various cross-domain settings.
Read the full abstract

All authors Luqi Sun, Shreeram Suresh Chandra, Aurosweta Mahapatra, Emily Mower Provost, Brian MacWhinney, Berrak Sisman

Sound · Cross-listed from eess.AS

HARP: Agentic Hybrid Retrieval and Analysis for Long-Form Audio

Chin-Jou Li, Masao Someki, Woojeong Jin et al. (+4 more)

Long-form audio analysis requires systems to localize and integrate evidence distributed across extended recordings. While existing work primarily retrieves semantic content through structured textual representations, many real-world queries depend on acoustic evidence that is better preserved in continuous representations or raw audio. We introduce HARP (Hybrid Audio Retrieval Pipeline), an agentic framework and benchmark for systematically studying retrieval and evidence representations in long-audio analysis. Hybrid retrieval combining keyword and vector search shows the most robust performance. When paired with both metadata and retrieved audio as evidence, average answer accuracy improves by around 10% and rationale accuracy by around 6% over single-modality retrieval and evidence. Fine-grained evaluation shows that answer accuracy alone overestimates system capability and that HARP mostly follows human performance trends across query types. These results highlight the importance of combining structured retrieval with flexible access to audio evidence and evaluating long-audio systems beyond answer accuracy.
Read the full abstract

All authors Chin-Jou Li, Masao Someki, Woojeong Jin, Yashish M. Siriwardena, Tanmay Laud, Shanil Puri, Shinji Watanabe

Sound

StepAudio 3 Realtime Technical Report

Bin Lin, Bo Zhao, Boyang Zhang et al. (+87 more)

Realtime spoken interaction demands deep reasoning, prompt responses, and fluid turn-taking. We present StepAudio 3 Realtime, an audio-language foundation model organized around a continuous listen-converse-think-act loop. Deep Perception captures rich acoustic cues to interpret user intent, while Seamless Duplex models synchronized audio streams to handle pauses, backchannels, and interruptions naturally. Crucially, we resolve the tension between deep deliberation and latency via Think-While-Speaking, executing private reasoning in parallel with spoken delivery. In reasoning mode, StepAudio 3 reaches a 73.0 macro average on StepAudioChat. With Think-While-Speaking, it achieves dialogue and reasoning performance comparable to dedicated reasoning models while speaking in real time. Furthermore, an integrated Voice Agent handles asynchronous tool execution without disrupting the dialogue flow. StepAudio 3 Realtime achieves top-tier performance across key dimensions: an exceptional 90.6 on the MMSU benchmark, 98.9 Overall on the Artificial Analysis Full-Duplex Bench, and a 56.0% macro task-success rate on $\tau$-Voice.
Read the full abstract

All authors Bin Lin, Bo Zhao, Boyang Zhang, Boyong Wu, Chao Yan, Chen Geng, Chen Wu, Cheng Yi, Chengli Feng, Chenglin Zhu, Chengting Feng, Chengyuan Yao, Daijiao Liu, DanNi Wan, Daxin Jiang, Dongjian Li, Dongqing Pang, Fei Tian, Feng Tian, Future Li, Gang Yu, Guanglong Yang, Haoyang Zhang, Hongyuan Wang, Jia Peng, Jiahao Song, Jialong Xue, Jiamin Fan, Jiangjie Zhen, Jianzheng Gao, Jincheng Wen, Jinghua Liang, Jinglan Gong, Jun Chen, Li Xie, Liang Zhao, Lifang Zhang, Lingli Ji, Lun Cai, Min Xu, Peilin Li, Peng Yang, Pengfei Tan, Qingjian Lin, Qinxin Du, Ruijie Xiong, Runze Li, Shenghua Hu, Shengqian Qin, Shi Qiu, Siqi Tu, Siyi Zhou, Tianjiao Deng, Wanying Lu, Weiming Niu, Wen Sun, WenWen Qu, Xiangyu Zhang, Xianwei Zhang, Xiaosu Su, Xing Chen, Xinyu Liu, Xuerui Yang, Yan Wu, Yang Li, Yang Yang, Yechang Huang, Yibo Zhu, Yifan Zhang, Yinuo Yan, Youjun Chen, Yu Fu, Yu Luo, Yu Zhou, Yujie Chen, Yumang Wang, Yunzhou Ju, Yuxiang Yang, Yuxin Li, Yuxin Zhang, Zekai Liu, Zengwei Yao, Zhaoxin Yuan, Zhenwei Mou, Zhiquan Zhang, Zhiyue Wu, Zichao Li, Zichao Zhou, Ziqi Ren, Zixuan Wang

Sound · Cross-listed from eess.AS

DualSpecSE: A Dual-Path Speech Enhancement Network Integrating Mel and Complex Spectrograms

Xingchen Li, Ziqian Wang, Zikai Liu et al. (+4 more)

In this paper, we propose DualSpecSE, a speech enhancement framework that jointly models Mel-spectrogram and complex spectrogram in a dual-path architecture for improved ASR performance and higher-quality speech reconstruction. The Mel branch learns coarse-grained acoustic representations and produces enhanced Mel-spectrograms for direct ASR usage, while the complex branch refines fine-grained spectral details for high-fidelity waveform reconstruction. Built upon the cross-band and narrow-band blocks from CleanMel, DualSpecSE introduces an interaction module and a fusion module to enable effective information exchange between the two branches. The model simultaneously outputs enhanced Mel and complex spectrogram without requiring a pretrained vocoder. Experimental results demonstrate consistent improvements in speech fidelity, perceptual quality, and ASR performance. Codes and audio samples are available.
Read the full abstract

All authors Xingchen Li, Ziqian Wang, Zikai Liu, Yike Zhu, Zihan Zhang, Longshuai Xiao, Lei Xie

Sound

DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech Synthesis

Ziyu Zhang, Tianlun Zuo, Hanzhao Li et al. (+2 more)

Continuous-latent Autoregressive Diffusion Transformer (AR-DiT) models have demonstrated immense potential in zero-shot speech generation. However, they still suffer from limited decoding stability when synthesizing long utterances or complex linguistic structures. This instability primarily stems from a restricted historical receptive field and an acoustic inertia dependency within the diffusion decoder, which causes the model to ignore semantic conditions. To address these challenges, we propose DiTAR+, a dual-optimization framework. First, we introduce Dilated Context Sampling to expand the macro-level historical receptive field without violating physical temporal continuity, thereby preventing cumulative error propagation. Second, we propose Hierarchical Acoustic Masking to prevent shallow layers from attending to acoustic pre-context, explicitly decoupling semantic alignment from acoustic detail reconstruction. Extensive experiments show that our framework effectively mitigates pronunciation errors and semantic hallucinations, enhances generation robustness on challenging sentences, and maintains exceptionally high speaker similarity throughout the entirety of long-form utterances. On the linguistically challenging ZH-Hard set, DiTAR+ reduces the word error rate from 12.478% to 9.893%, and on extended utterances of 25 to 35 seconds it improves speaker similarity from 0.741 to 0.759 while simultaneously lowering the word error rate from 2.778% to 2.173%, outperforming both discrete-token and pure flow-matching baselines.
Read the full abstract

All authors Ziyu Zhang, Tianlun Zuo, Hanzhao Li, Haoyu Zhang, Lei Xie

Sound

Musical Timing in Studio Recordings

Konstantinos Tsioutas and George Xylomenos

Studio recording techniques vary considerably, ranging from live recordings in a shared acoustic space, to isolated booth recording and overdubbing, where musicians record their parts separately, while listening to previously recorded material. These approaches differ in terms of physical co-presence, visual contact, sound leakage, and acoustic isolation, factors that may influence musical coordination. This study investigates whether the recording style affects timing precision; specifically, whether musicians performing together in the same space achieve tighter temporal coordination. To address these questions, two datasets with a total of 391 multi-track recordings were analyzed to measure the timing relationships between musicians. In addition, an automated sound-leakage detection method was employed to infer the recording conditions of each song: pairwise Mel-spectrogram similarities between the tracks were computed, and summary statistics from the resulting similarity matrices were used to identify recordings with shared acoustic content. The results suggest that recordings showing evidence of shared room acoustics and sound leakage tend to exhibit lower timing variability than highly isolated recordings, whereas overdubbing is associated with increased timing variability.
Read the full abstract

Sound

CRAF: Cross-View Residual-Aware Fusion for Deepfake Speech Detection

Minh-Xuan Phan, Khalid Zaman, Candy Olivia Mawalim et al. (+1 more)

Recent advances in speech synthesis and voice conversion have made deepfake speech increasingly realistic, making generalization to unseen spoofing attacks a critical challenge. Pretrained speech and audio models offer a promising direction for improving robustness to such unseen attacks. Self-supervised learning (SSL) models capture fine-grained, low-level acoustic characteristics, whereas Auditory Large Language Models (ALLMs) provide higher-level contextual representations. These complementary views can provide useful cues for improving generalization to unseen attacks. However, direct fusion does not explicitly disentangle information shared across the two views from view-specific complementary information, limiting effective cross-view integration. To address this, we propose CRAF, a cross-view residual-aware fusion framework that uses ALLM-guided cross-view attention to enrich SSL representations and adopts ALLM as a high-level reference to separate ALLM-explainable information from complementary SSL residual information. The residual is selectively refined through adaptive gating and integrated through SSL-primary fusion. Experiments on ASVspoof 5 show that CRAF with Kimi-Audio achieves an EER of 5.96% and a minDCF of 0.1192, demonstrating robustness to unseen spoofing attacks.
Read the full abstract

All authors Minh-Xuan Phan, Khalid Zaman, Candy Olivia Mawalim, Masashi Unoki

Sound

The VoiceMOS Challenge 2026: Evaluating Speech Enhancement, Emotional TTS and Accented TTS Systems

Wen-Chin Huang, Wei Wang, Marvin Sach et al. (+4 more)

We present the results of the VoiceMOS Challenge 2026, the fifth edition of a scientific challenge on automatic prediction of subjective speech assessments. After expanding the scope to music and general audio in 2025, we refocused the evaluation target on speech and organized three tracks: prediction of absolute and comparative category ratings for enhanced speech, prediction of naturalness and emotion-related tasks for emotional text-to-speech systems, and prediction of speaker and accent similarity for codec-based speech synthesis systems. The challenge attracted a total of 18 teams worldwide, with most teams successfully surpassing the provided baselines. We summarize the challenge results, representative top-performing systems, participant feedback, and directions for future editions.
Read the full abstract

All authors Wen-Chin Huang, Wei Wang, Marvin Sach, Xiaoxue Gao, Nicholas Sanders, Erica Cooper, Toda Tomoki

Sound · Cross-listed from eess.AS

Subphonetic Acoustic Modeling via Optimal Transport for Pronunciation Assessment

Haopeng Geng, Jiun-Ting Li, Daisuke Saito et al. (+1 more)

Pronunciation assessment requires acoustic evidence that is temporally precise, diagnostically meaningful, and faithful to the learner's actual production. However, existing acoustic models often struggle to provide recognition and segmentation evidence simultaneously. CTC-based phone recognizers can predict phone sequences flexibly, but their sparse and peaky posteriors often miss phone boundaries and fine-grained pronunciation cues. In contrast, text-dependent forced aligners provide reliable temporal information when transcripts are available, but are not directly applicable to reference-free pronunciation analysis. In this work, we propose a topology-aware frame-wise acoustic model that learns dense ordered state posteriors within each phone. The key idea is to recover phone-internal state structure in a neural acoustic model by combining ordered subphonetic states with optimal temporal transport classification (OTTC). This combination encourages dense monotonic frame-level state discrimination while preserving phone recognition ability. Experiments on read, spontaneous, and L2 speech show improved segmentation over neural baselines with competitive recognition performance. Downstream evaluations further show gains in mispronunciation detection and automatic pronunciation assessment. Probing analysis suggests that the learned states capture phoneme-dependent acoustic structure rather than arbitrary frame-level distributions.
Read the full abstract

All authors Haopeng Geng, Jiun-Ting Li, Daisuke Saito, Nobuaki Minematsu

Sound

UniqueShip: Mitigating Data Leakage in Acoustic Ship Classification Benchmark Datasets

Connor Hashemi, Trevor Stout, Anthony Hoogs et al. (+1 more)

Underwater Acoustic Target Recognition (UATR) of ships is well-suited for machine learning, yet its progress is hindered by the lack of large, diverse, and publicly available labeled datasets. In this work, we introduce UniqueShip, a machine learning-ready benchmark dataset for UATR applications sourced from the open Ocean Networks Canada (ONC) repository. Unlike previous datasets, we explicitly control for "data leakage" between the training and evaluation sets to ensure more reliable and generalizable model evaluation that does not encourage the model to memorize individual ships. We demonstrate that typical, random data partitioning in two prominent UATR datasets leads to falsely optimistic test performance, increasing accuracy by 10-48 percentage points compared to our more careful partitioning. Ablations on UniqueShip further show that doubling the number of unique vessels improves accuracy by 2.4-2.6 percentage points, while doubling total audio duration improves only by 0.8-1.3 points, indicating that vessel diversity should drive dataset curation more than total hours. We provide baselines with convolutional and transformer backbones, and analyze how ship metadata correlates with classification performance, finding that individual vessel characteristics predict classification difficulty far better than distance to the hydrophone alone. Overall, UniqueShip contains 2,460 hours of ship-radiated audio from 4,218 unique vessels (3,437 hours including background). We publish the dataset, code, and easy-to-download splits at uniqueshipdata.org to foster further UATR research.
Read the full abstract

All authors Connor Hashemi, Trevor Stout, Anthony Hoogs, Jason Parham

Friday 11 September

Sound · Cross-listed from eess.AS

StepAudio 3 Music Technical Report

Chengli Feng, Zhiyue Wu, Jiahao Song et al. (+10 more)

We introduce StepAudio 3 Music, a large-scale, long-form music generation model that supports explicit musical planning and open-domain text-controlled generation. The StepAudio Music Tokenizer represents audio as a 50-Hz stream from a 65536-entry single codebook, using semantically informed self-supervised and multi-task training to preserve musical structure and reconstruction-relevant information. A flow-matching diffusion Transformer (DiT) predicts continuous StepAudio VAE latents, which our VAE decoder converts into 48-kHz audio. This discrete-continuous design is guided by comparisons of single-codebook VQ, Semantic and Acoustic RVQ, and different DiT configurations. For explicit planning, a Mixture-of-Experts autoregressive model uses ABC notation to produce an intermediate arrangement plan (ABC-CoT) before predicting music tokens, making harmony, rhythm, and melodic structure part of the generation context. A progressive training curriculum and supervised fine-tuning support song and instrumental generation, accompaniment generation from dry vocals, and cover-song synthesis for up to 5 minutes and 30 seconds. With reinforcement learning via direct preference optimization (DPO), the final model achieves the highest AudioBox Content Enjoyment, Content Usefulness, and Production Quality scores and the highest MuQ-MuLan similarity among the evaluated systems, with competitive SongBench results. On the preliminary Artificial Analysis Music Arena Vocals leaderboard, it obtains a Quality Elo of 1105, behind only Suno V5.5 and Mureka and ahead of Suno V5, MiniMax models, and other systems. Audio demonstrations are available at https://stepaudiollm.github.io/step-audio-3-music.
Read the full abstract

All authors Chengli Feng, Zhiyue Wu, Jiahao Song, Zheqi Dai, Boyang Wang, Ruibin Yuan, Junming Gong, Wenxiao Zhao, Jing Guo, Gang Yu, Xiangyu Zhang, Xuerui Yang, Chao Yan