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 5 October

Sound

Exposing and Mitigating Neural Codec Vulnerabilities in Audio Deepfake Detection

Abdullah, Awais Khan and Khalid Mahmood Malik

Existing audio deepfake detection (ADD) datasets and detectors are primarily built for vocoder-based synthesis, evaluated against traditional post-hoc perturbations such as MP3/AAC compression or additive noise, applied independently of generation. However, recent speech synthesizers, particularly ALM-based systems, use neural audio codecs both for compression and as the resynthesis reconstructing waveforms from generated tokens, producing artifacts distinct from post-hoc compression. Neural codecs thus play a dual role: some are designed for pure compression under low-bandwidth communication, while others serve as resynthesis components. Despite this dual role, robustness to codec-based compression, unlike post-hoc compression, remains largely unexplored. We expose this gap, showing that state-of-the-art (SOTA) ADD models degrade drastically on codec-compressed speech; in particular, systems trained on Codec Resynthesized data as a proxy for codec-based generation prove most vulnerable, with legitimately compressed bona fide speech often misclassified as fake. To investigate this, we construct the Audio Neural Codec-Spoof dataset by applying seven neural codec algorithms to existing ADD benchmarks, isolating codec-induced resynthesis artifacts as a controlled proxy for codec-based generation. As baseline mitigation, we propose PCL-NET (Pairwise Consistency Learned Network), fine-tuning a pretrained XLS-R (300M) encoder with a pairwise consistency objective that minimizes the representation distance between an utterance's uncompressed and codec-compressed versions, disentangling codec artifacts from the real-versus-fake decision. As a result, PCL-NET reduces average EER under neural codec compression from 28.67% to 12.77%, while preserving competitive CoSG-based deepfake detection performance. We will also make the dataset publicly available on Hugging Face upon acceptance.
Read the full abstract

Sound

Neural Representations, Natural Connections: What Transfers From Human Speech Foundation Models to Animal Vocalizations?

Tomás Arias-Vergara, Christopher Hauer, Héloïse Brotier et al. (+3 more)

Speech-pretrained models have shown promise in animal bioacoustics, but the factors governing their cross-species transfer remain poorly understood. We evaluate 15 frozen encoders spanning monolingual and multilingual speech, speaker verification, animal bioacoustics, and general audio on caller identification across four species and call-type classification across three. Differences between the strongest speech- and animal-pretrained representations range from $-0.027$ to $+0.119$ UAR; speech is significantly better in three of seven settings ($p<0.01$) and not significantly different in the remaining four. Controlled comparisons show no systematic advantage from increased language coverage or animal-domain pretraining, while frozen speaker-verification embeddings transfer poorly. The results also show that transfer is strongly layer-dependent: raw-waveform models peak early, whereas patch-spectrogram models peak deeper.
Read the full abstract

All authors Tomás Arias-Vergara, Christopher Hauer, Héloïse Brotier, Elmar Nöth, Andreas Maier, Lee Koren

Sound

ImpactMat: Continuous Material Estimation for Inverse Impact Sound Rendering

Hyebin Cho, Bumsoo Kim and Joon Son Chung

Impact sound rendering synthesizes the sound produced when a 3D object is struck, but practical renderers often rely on fixed material presets such as wood, plastic, or steel. These presets limit the range of impact sounds a renderer can express, while manually adjusting the underlying material parameters remains difficult without expertise in material acoustics. We therefore study inverse impact sound rendering: predicting material parameters from a reference impact sound so that a simulator can recreate a similar material response. To support this task, we introduce ImpactMat, a dataset and benchmark of single and blended material impact sounds paired with ground-truth material parameters. We further propose a feed-forward model that predicts these parameters from one or more recordings, using blended materials to learn smooth transitions between material types. Experiments show that our method outperforms competitive baselines and enables re-rendering from real recordings without manual parameter tuning. The project page is available https://material-from-impact.github.io/material-from-impact/.
Read the full abstract

Sound · Cross-listed from eess.AS

SEAL: Mixture-Closed Additive Reconstruction and Refinement-Aware Expert Routing for Efficient Speech Separation

Shao-Chun Hu, Zi-Xiang Lin, Jeih-Weih Hung et al. (+1 more)

Compact time-frequency separators that mask the mixture and refine through a shared cell face two limits. First, a bounded multiplicative mask only scales a mixture bin, so where overlapping components cancel, the estimate stays small. Second, a shared cell applies the same weights to every time-frequency token at every step, so enlarging it adds compute everywhere. We present SEAL (Sparse Expert routing with Additive Latent reconstruction) to address both. For reconstruction, a zero-sum additive residual bounded by the local mixture amplitude lets estimates be nonzero where components cancel yet still sum to the mixture. For routing, a query built from acoustic and inter-step evidence sends each token to one of six residual experts, and a norm cap keeps the step cue from overriding clear acoustic evidence. On EchoSet, SEAL (small) surpasses TIGER (small) by 0.31 dB SI-SDRi with 28% fewer parameters and 2.9 times fewer MACs, and SEAL (large) is within 0.07 dB SI-SDRi of TIGER (large) at 3.1 times fewer MACs.
Read the full abstract

All authors Shao-Chun Hu, Zi-Xiang Lin, Jeih-Weih Hung, Hung-Shin Lee

Sound · Cross-listed from eess.AS

GIVE-KWS: Gated Injection of Visual Evidence for Noise-Robust Query-by-Example Keyword Spotting

Ming-Hsiang Hu, Kuan-Tang Huang, Hung-Shin Lee et al. (+1 more)

Visual speech promises noise-robust keyword spotting, yet a visual stream is not necessarily used. On a tri-modal query-by-example keyword spotting (QbyE-KWS) benchmark, we find that a system with a task-trained visual encoder comes within 2 percentage points of a text-and-audio system in equal error rate (EER) at -10 dB, and link this gap to the encoder's lack of phonemic information. We present GIVE-KWS, whose fusion stage, GIVE (Gated Injection of Visual Evidence), conditions query audio on lip motion through gated cross-attention. We show that visual robustness depends on two interacting conditions: a phoneme-bearing visual representation, and fusion that injects visual evidence rather than rescaling audio features. Under a phoneme-bearing encoder, injection yields an effective SNR gain of 4.0-9.3 dB over masking at -10 dB, whereas under a phoneme-poor one it nearly vanishes. Relative to the benchmark system, GIVE-KWS reduces unseen-keyword EER by 72.9% at -10 dB and 62.8% on average.
Read the full abstract

All authors Ming-Hsiang Hu, Kuan-Tang Huang, Hung-Shin Lee, Berlin Chen

Sound

Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model

Sahil Mahendrakar

We distill Kokoro-82M, a widely used open text-to-speech model with 54 voices, into Paradee, an 8.07M-parameter model that speaks one of them. Paradee keeps Kokoro's architecture with much narrower layers, and each of its two halves is trained separately against the frozen teacher. It has 10x fewer parameters and needs 15x less compute. We first synthesize a corpus with the teacher and keep its durations, pitch, energy and phoneme features. We then train a small text side to predict these values, and a small decoder to turn the teacher's saved values into the teacher's audio, first with spectral losses and then adversarially. Finally, we connect the two halves and quantize the weights to int8. It needs no alignment learning and no joint training, and it runs on one laptop. Stored in int8, Paradee is 8.5 MB, runs 25x faster than real time on one CPU thread, and scores 4.41 on UTMOS against the teacher's 4.52. The student initially kept a slight buzz, which we trace to the phase of voiced speech between 2 and 8 kHz. A phase-locking filter applied after synthesis removes most of it, with no training and no extra parameters. Code, model files and audio samples are at https://github.com/sahilmahendrakar/paradee
Read the full abstract

Sound

Revisiting Label-Free Speaker Embedding Enhancement with vMF Profile Likelihood

Seunghwan Kim, Jinyong Kim, Sooyoung Yang et al. (+2 more)

Embedding enhancement improves speaker verification under acoustic mismatch without modifying a frozen backbone. Recent work has established a practical label-free setting for this task, but often adopts increasingly structured formulations. Here, the clean target is directly observed during training, making enhancement a matching problem on the unit hypersphere. We model the clean target with a von Mises–Fisher (vMF) likelihood and profile out a sample-wise concentration parameter, yielding a simple closed-form objective with adaptive weighting. Across VoxCeleb1, VoxSRC23, CN-Celeb, VOiCES, and VC-Mix, the proposed method largely preserves the baseline and gives clearer gains on challenging mismatch sets. It also remains stable under a broad single-view recipe, where a recent diffusion baseline becomes less reliable in controlled comparisons. These results suggest that effective label-free embedding enhancement in this setting does not require a highly structured formulation.
Read the full abstract

All authors Seunghwan Kim, Jinyong Kim, Sooyoung Yang, Youngjin Ko, Myungjoo Kang

Sound

AuraSE: Low-Hallucination Generative Speech Enhancement via Multimodal Flow Matching and Inference Policy Optimization

Yingda Shen, Yao Qian, Yuxuan Hu et al. (+7 more)

Generative speech enhancement models can produce cleaner and more natural-sounding speech than conventional discriminative approaches, but may hallucinate by changing speech content or speaker identity, even with transcript conditioning. We present AuraSE, a flow-matching framework that addresses hallucination through complementary modality and inference designs. First, a double-stream-to-single-stream multimodal Diffusion Transformer (MMDiT) allows transcript and acoustic representations to interact while preserving a dedicated pathway for the degraded input. Second, we find that the best decoder configuration, governed by guidance scale, sampling temperature, and step count, varies substantially across utterances. This observation motivates Inference Policy Optimization (IPO), an online, on-policy preference optimization method. IPO generates multiple candidates from the current model under different inference configurations, ranks them with a multi-objective reward, and learns from their relative preferences. AuraSE-IPO ranks first on 11 of 12 metrics across the synthetic test sets and obtains the highest DNSMOS and blind-listening scores among the evaluated systems on the real DNS blind test set. At deployment, it uses a fixed $10$-step ODE decoder without classifier-free guidance (CFG) or per-utterance configuration search.
Read the full abstract

All authors Yingda Shen, Yao Qian, Yuxuan Hu, Junan Zhang, Yuxiang Wang, Hardik Hansrajbhai Chauhan, Yudong Li, Yufei Xia, Yufei Liu, Zhizheng Wu

Sound

Mind the Accent Gap: British Accent Robustness in Speech-Driven Financial Voice Assistants

Aadam Haq, Oggi Rudovic, Malcolm Chadwick et al. (+5 more)

AI voice assistants often use Automatic Speech Recognition (ASR) with LLM-based reasoning, yet existing systems struggle with regional British accents, including Scottish, Irish, and Welsh accents, since most ASR models are trained predominantly on American English voice data. Consequently, errors can carry through to the LLM stage, corrupting tool-call arguments and producing wrong or missing responses, which is especially costly in finance. Deployable ASR must also meet tight latency and memory budgets, making an accent-robust model choice even harder. We introduce CavaBench, the first internally collected benchmark of spoken financial queries, and use it to evaluate a range of ASR models and their end-to-end ASR-LLM pipeline behaviour across self-reported British accents. We find that WER strongly predicts downstream tool-calling accuracy ($r = -0.93$) but can fail to reflect task-level performance, with accent-related failures varying substantially across models and acoustic conditions. These findings guide the design of more inclusive, reliable voice-based financial assistants.
Read the full abstract

All authors Aadam Haq, Oggi Rudovic, Malcolm Chadwick, Jay Rainey, Shucong Zhang, Ricardo Guerrero, Sourav Bhattacharya, Maja Pantic

Sound · Cross-listed from eess.AS

Ensemble-Based Perceptual Audio Quality Assessment with Confidence Intervals

Pablo M. Delgado, Andreas Brendel, Konstantin Schmidt et al. (+1 more)

Objective audio quality metrics typically provide point estimates, whereas listening tests yield score distributions from which mean opinion scores (MOS), confidence intervals (CIs), and significance decisions are derived. We propose a lightweight intrusive metric that combines a PEAQ-style perceptual front-end (ITU-R BS.1387) with a bagging ensemble of regressors. Calibration with subjective data aligns ensemble outputs with listener scores. The resulting item-dependent score distributions enable uncertainty assessment, panel-size-matched CIs, and identification of less conclusive predictions. Calibration improves agreement with subjective distributions and CI coverage across all evaluated datasets while preserving MOS accuracy. Using only 11 fixed PEAQ features, low-capacity regressors, and public training data, the method performs comparably to more data-intensive end-to-end approaches. Its output can support uncertainty-aware assessment and target listening tests towards uncertain conditions. The distributions also enable approximate pairwise comparisons, but not yet reliable significance inference.
Read the full abstract

All authors Pablo M. Delgado, Andreas Brendel, Konstantin Schmidt, Jürgen Herre

Sound

Smorph: Playable Sound Morphing with Diffusion Models

Annie Chu, Hugo Flores García, Johannes Imort et al. (+5 more)

Sound morphing, generating intermediate sounds that transition from one sonic identity to another, can be a powerful tool for musical sound design. Existing diffusion-based morphing approaches entangle temporal structure and timbral identity, offering no mechanism to hold one fixed while transforming the other. We present smorph, a training-free guidance framework that preserves how a sound behaves over time while transforming what the sound is, allowing users to morph, for instance from brass to strings at a fixed pitch. We demonstrate across three morphing modes: prompt-to-prompt, audio-to-prompt, and audio-to-audio. Evaluations across diverse datasets show that smorph effectively produces smooth morph trajectories while substantially improving temporal-structure and source preservation over baselines, albeit with more conservative target-ward transformation in some settings. In an exploratory case study, musicians found smorph trajectories to be expressive and playable, suggesting structural anchoring can serve as a productive constraint for instrumental interaction.
Read the full abstract

All authors Annie Chu, Hugo Flores García, Johannes Imort, Oriol Nieto, Bryan Pardo, Jordan Rudess, Prem Seetharaman, Justin Salamon

Sound · Cross-listed from cs.CL

Do Speech Representations Preserve Regional Accent Across Read and Spontaneous Speech?

Paula A. Perez-Toro, Tomas Arias-Vergara, Annette Schwarz et al. (+4 more)

Regional accent cues can be captured under matched conditions, but it remains unclear whether they persist between read and spontaneous speech. We study RVG1, with 500 German speakers from nine regions, comparing ten speech representations on regional classification and continuous geolocation under matched conditions and speaker-independent read–spontaneous transfer. Whisper performs best under matched conditions, reaching 0.489 nine-way UAR and 148 km median geolocation error, but drops to 0.11/0.18 UAR across transfer directions and 363 km geolocation error. Self-supervised models show a similar degradation, whereas speaker embeddings are less discriminative in-domain but more robust under transfer. This contrast is consistent across classification and geolocation. Across representations, robustness is associated with how little a representation shifts between styles (style-invariance), for which crossstyle speaker retrieval is an interpretable proxy. Age, sex, sentence-overlap, and duration controls do not account for the gap, although channel characteristics contribute. These results show that strong matched-condition performance does not indicate robust regional information.
Read the full abstract

All authors Paula A. Perez-Toro, Tomas Arias-Vergara, Annette Schwarz, Abner Hernandez, Andreas Horr, Cornelia Kristen, Andreas Maier

Sound

A Comprehensive Objective Evaluation of Modern Text-to-Speech for Turkish Using Speech Quality Assessment Models

Yunus Emre Ozkose, Alperen Kahraman and Ali Haznedaroglu

Modern text-to-speech (TTS) systems can clone a target speaker from a short reference clip or be fine-tuned on a target voice, yet their behaviour on morphologically rich, lower-resource languages such as Turkish remain under-characterised. We present a systematic benchmark of four contemporary systems (Chatterbox, CosyVoice, OmniVoice, and VoxCPM2) evaluated across fine-tuned and zero-shot configurations, contrasted with a conventional VITS baseline and anchored to natural gold speech. Each configuration is scored with eighteen complementary objective metrics spanning learned naturalness predictors (UTMOS v2, DNSMOS-Pro, SCOREQ, WhisQA, AudioBox-PQ, NatScore, SpeechLMScore), intelligibility and signal-quality estimators (SQUIM PESQ/SI-SDR/STOI, Brouhaha), speaker similarity, distributional fidelity (TTSDS) and low-level acoustic descriptors. We further analyse how quality varies with utterance length and quantify long-form temporal consistency through speaker-identity and naturalness drift over chunked utterances. We release our evaluation code to support reproducible TTS evaluation.
Read the full abstract

Sound · Cross-listed from eess.AS

Character Identity is not Speaker Identity: KyaraBench and KyaraEmbed for Character Verification

Joonyong Park and Jerry Li

A dubbed character keeps its identity while the voice actor changes, so character identity and speaker identity are distinct properties of one recording, yet speaker verification measures only the latter. To address this gap, we propose KyaraBench, a benchmark that scores character voice directly instead of speaker voice, built from 85 human-audited identities in a dubbed anime corpus. It poses two challenging conditions: one that swaps the performer under a fixed character, and one that fixes the performer under changing characters. Listening studies with 78 participants provide human reference scores for cross-performer verification and same-actor discrimination. Speaker-verification baselines show increased errors under these character-specific conditions. We then train KyaraEmbed, a compact encoder using multilingual character supervision, same-actor negatives, and a language-alignment term. The model achieves the best performance on all character-specific conditions in the main comparison. We release the benchmark, protocol, and encoder publicly.
Read the full abstract

Sound · Cross-listed from cs.CV

UltraDub: Towards Authentic Dubbing by Unifying Visually-Steered Flow Learning and Trajectory Guidance

Gaoxiang Cong, Liang Li, Jianwei Wen et al. (+3 more)

Visual voice cloning requires intelligible, speaker-consistent speech synchronized with visible articulation. However, sequential multimodal conditioning can disrupt previously established temporal and speaker cues, while imbalanced inference guidance can improve linguistic accuracy at the expense of lip synchronization. In this paper, we propose UltraDub, a Unifying Visually-Steered Flow learning and trajectory Guidance Dubbing framework that leverages vision in two ways: as continuous motion for multimodal context aggregation, and as structural rhythm for trajectory rectification. Specifically, we introduce the Motion-guided Dual-context Retrieving (MDR) module, which continually recalibrates linguistic and speaker-style retrieval through shared lip-motion query residuals, utilizing independent time-conditioned gates to regulate their contributions. Furthermore, we propose Rhythm-anchored Trajectory Guidance (RTG), a training-free mechanism that evaluates hierarchical multimodal corrections at a visual-only predictive midpoint, safely strengthening semantic conditioning while better preserving temporal alignment. Finally, we construct DiverseDub, a multi-scenario benchmark to evaluate video dubbing in the wild. Extensive experiments demonstrate that UltraDub achieves state-of-the-art performance across four datasets.
Read the full abstract

All authors Gaoxiang Cong, Liang Li, Jianwei Wen, Zhedong Zhang, Zheng-Jun Zha, Qingming Huang

Sound

Relational Synthesis: Structure-Mediated Concatenative Synthesis for Foley and Retrieval-Augmented Audio Generation

Keren Shao, Ayaka Kawano and Shlomo Dubnov

We ask: given a retrieved source audio $S$ and a separate reference audio $R$, can we synthesize novel audio $Y$ out of this pair $(S,R)$ such that $Y$ remains acoustically consistent with $S$, while not persistently copying segments of $S$ or $R$? The first clause is a well-known goal in Foley audio production, and the second is a well-known issue in neural RAG when $S$ and $R$ are naively injected into neural generators. We show that both clauses can be addressed simultaneously using a method we coin relational synthesis, a variation of concatenative synthesis where target cost is replaced by a relational Gromov-like structural cost. Rather than imitating the content of $R$, relational synthesis exploits it from the "other side of the hill": it transfers the temporal structure and directed amplitude motion of $R$ to reorganize and concatenate the grains of $S$ in a novel manner that protects $S$'s acoustic information. Our experiments show that relational synthesis integrates naturally with neural RAG and produces Foley audio that performs well on metrics measuring temporal agreement, acoustic fidelity, and leakage persistence, while maintaining distribution-level quality and text alignment.
Read the full abstract

Sound · Cross-listed from eess.AS

Revisiting Frame-Wise Saliency for Audio Moment Retrieval

Tatsuya Komatsu and Hokuto Munakata

This paper revisits frame-wise saliency for audio moment retrieval (AMR). We show that the frame-wise saliency sequence, conventionally used only as an auxiliary output in DETR-based AMR models, can itself serve as an effective source of moment predictions. We convert the saliency sequence into ranked moments using a simple SED-inspired segmentation rule with no learned parameters, enabling moment retrieval directly from frame-wise temporal information. On the CASTELLA dataset, saliency-based prediction consistently outperforms decoder-based prediction from the same model across all 18 runs of QD-DETR and CG-DETR. For QD-DETR, simply replacing the inference output improves R1@0.7 from 21.0 to 36.1. The advantage remains 7-15 points when the two outputs are evaluated at their independently selected best epochs. The same tendency extends to TaskWeave and UVCOM, whereas TR-DETR shows the opposite behavior, suggesting that how saliency construction may matter. The performance gap is especially pronounced for short moments: for queries whose annotated moments average at most 2 s, R1@0.7 improves from 6.3 to 27.8 with QD-DETR. Decoder supervision nevertheless benefits saliency-based prediction, indicating that its role during training differs from the utility of its inference output.
Read the full abstract

Sound

AudioGAR: Bridging Reconstruction and Generation in Latent Audio Generative Models

Xianghong Fang, Geeyang Tay, Wentao Ma et al. (+2 more)

Latent audio generative models are typically trained in two stages: an audio codec is learned first, followed by a latent generative model. This decomposition leads to a decoder train-generation mismatch: the codec decoder is trained on encoder-induced latents but deployed on generator-produced latents at inference time. Across diverse datasets and latent generative models, we observe clear reconstruction-generation gaps under both FD and FAD, showing that strong reconstruction quality does not necessarily translate into strong end-to-end generation quality. A natural remedy is to adapt the decoder on generation-produced latents, but generated latents lack correspondence with source audio and therefore cannot directly provide the paired supervision used for decoder fine-tuning. We introduce AudioGAR, which constructs intermediate latents by perturbing encoder latents and denoising them through the frozen latent diffusion model. These latents form a trajectory from reconstruction toward generation, with lower-noise latents retaining source correspondence and supporting paired decoder fine-tuning. We fine-tune only the codec decoder on these latents, while keeping the codec encoder and latent generative model frozen. When applied to AudioX, AudioGAR substantially improves generative performance. It requires only 1.5% of the original training audio hours and 0.26% of the original training cost.
Read the full abstract

All authors Xianghong Fang, Geeyang Tay, Wentao Ma, Tim G. J. Rudner, Dehan Kong

Sunday 4 October

Sound

Where Does the Audio Jailbreak Live? A Controlled Frequency-Depth Audit of AdvWave-P on Qwen2-Audio

Boyuan Chen, Minseok Kim, Sohaila Abdulsattar et al. (+4 more)

We audit frequency and decoder-depth claims for AdvWave-P, an additive audio jailbreak, on Qwen2-Audio. The protocol masks frequency components of the perturbation in the short-time Fourier transform (STFT) domain and measures attack success and audio-span representations. On 520 AdvBench prompts, the primary judge labels 76.7% of adversarial inputs as jailbreaks. A condition-blind, single-annotator validation yields a Rogan-Gladen sensitivity estimate of 0.87 for this condition (about 0.83-0.95 with validation-rate uncertainty); this correction is not applied to masked conditions. The apparent frequency ranking depends on the partition: energy share alone predicts the standard eight-band ranking (Spearman's rho = 0.95), and equal-Hz and equal-energy partitions show that masking any tested band can sharply reduce attack success. At a finer 16-band equal-energy resolution, however, masking the narrow 7520-7960 Hz band leaves ASR at 0.10, which remains unresolved without a matched control. Matched-energy scattered-removal tests show that contiguous removal is more damaging in lower bands, while both forms approach the floor in upper bands. Global rescaling leaves ASR near baseline but tests amplitude sensitivity rather than frequency location. In a re-optimization pilot (n = 20), tested single- and two-band supports reach ASRs of 0.00, 0.25, and 0.40, while random supports covering about half the STFT bins reach a mean of 0.86. In a prompt- and energy-adjusted model, audio-span divergence is associated with band necessity, with the coefficient rising from +0.63 at the projector output to +0.93 at layer 30 (contrast +0.293, 95% CI [0.11, 0.51]). This association is not a causal localization, and single-layer patching does not establish a causal layer. The results support partition-aware auditing of frequency claims, leaving the fine-resolution top-band result and broader generality open.
Read the full abstract

All authors Boyuan Chen, Minseok Kim, Sohaila Abdulsattar, Minghao Shao, Siddharth Garg, Ramesh Karri, Muhammad Shafique

Sound

SEA-LM: Egocentric Spatial Audio Understanding for Wearable Microphone Arrays

Sonal Kumar, Sinan Hersek, Artem Dementyev et al. (+6 more)

Embodied, ego-centric intelligence fundamentally requires the ability to comprehend spatial audio within complex environments. While large audio-language models excel at mono-channel reasoning, they lack spatial awareness, discarding critical spatial cues that enable sound localization and that can improve the disentanglement of overlapping sound sources. To address this, we present SEA-LM, a Spatial Audio Understanding model. First, we introduce FOACODER, a layout-flexible spatial audio encoder trained on source localization and ego-centric voice activity detection objectives to encode First Order Ambisonics derived from variable-count, variable-position smart-glasses arrays via beamforming. We train a Multimodal Large Language Model (MLLM) to understand these spatial audio embeddings through a two-stage curriculum spanning six tasks, including sound localization and spatially selective transcription in settings with multiple speakers and overlapping sounds. To prevent the transcription outputs from dominating the next token prediction loss and overwhelming the direction predictions, we introduce a Spatio-temporal Weighted Cross-Entropy Loss. On our evaluation set, SEA-LM achieves lower azimuth and elevation MAE, higher temporal IoU, lower external-source hallucination and missing-source rates, and lower WER on most transcription tasks than compared baselines, while remaining robust across 1,211 smart-glasses array configurations with 4 to 9 microphones.
Read the full abstract

All authors Sonal Kumar, Sinan Hersek, Artem Dementyev, Mengzhen Pan, Ishan Chatterjee, Anurag Kumar, Ramani Duraiswami, Dinesh Manocha, Andrea Colaco

Sound

SheetSage2: Coherent Lead-Sheet Transcription with Synthetic Supervision

Junyan Jiang, Ruibin Yuan, Jiahao Pan et al. (+4 more)

Transcribing music into a human-readable score requires a coherent understanding of rhythm, harmony, melody, and form. Two obstacles limit this goal: annotated recordings are scarce, and accurate local predictions can still produce inconsistent musical sequences. We present SheetSage2, a unified music transcription framework that combines synthetic data, task-specific structured decoding, and autoregressive distillation. Automatically annotated MIDI, rendered into audio, provides scalable supervision across music understanding tasks. Task-specific structured decoders integrate complementary musical cues and their temporal dependencies to produce musically coherent scores. Autoregressive distillation further retains transcription accuracy without task-specific dynamic programming at inference. Across eight benchmark collections, a single SheetSage2-AR model exceeds the listed prior systems on 12 of 15 benchmark–metric pairs in our evaluation, substantially improving over SheetSage1 and surpassing task-specific models on several benchmarks. Model weights and inference code are publicly available.
Read the full abstract

All authors Junyan Jiang, Ruibin Yuan, Jiahao Pan, Wei Xue, Yike Guo, Gus Xia, Yann LeCun

Sound

Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection

Miao He, Peng Cheng, Zhongjie Ba et al. (+4 more)

Advances in speech synthesis have made deepfake speeches increasingly convincing, posing growing threats to security. While self-supervised learning (SSL) based detectors achieve state-of-the-art performance, their computational demands (typically 300M+ parameters) prevent deployment on resource-constrained devices. Existing compression methods, designed mainly for content-centric tasks, struggle to maintain competitive performance when directly adapted to deepfake detection. We propose a Task-Aware Joint Pruning and Distillation framework that combines cross-domain knowledge distillation with movement-guided structured pruning to transfer forgery-discriminative knowledge and preserve critical structures under aggressive compression. Our framework reduces the model to 31.9M parameters with 6.3$\times$ FLOPs reduction, with an average performance drop of only 1.30% across multiple datasets compared to the uncompressed baseline, demonstrating strong potential for on-device deployment.
Read the full abstract

All authors Miao He, Peng Cheng, Zhongjie Ba, Qing Wen, Li Lu, Xin Yang, Kui Ren

Sound

NeuMark-Native: Robust Text-to-Speech-Native Watermarking Through Full Utilization of Neural Audio Codec Latent Space

Annan Wu, Wen-Chin Huang and Tomoki Toda

Speech watermarking offers proactive traceability for synthetic speech, yet most existing models operate only after text-to-speech (TTS) synthesis by adding a watermark perturbation to the generated waveform. This post-hoc design leaves watermarking as an external step that can be omitted or bypassed and restricts the watermark to a shallow waveform representation. We propose NeuMark-Native, a TTS-native watermarking framework for neural codec-based synthesis. It embeds payload information into every generated codec-latent layer before waveform decoding, improving watermark persistence under downstream digital signal processing (DSP) and neural codec resynthesis. NeuMark-Native keeps the pretrained TTS model and the neural codec frozen, while optimizing only the watermark modules on generated codec tokens. Experiments on two corpora under 11 DSP attacks and 9 neural-codec attacks demonstrate robust watermark detection while preserving naturalness, intelligibility, and speech quality close to synthetic speech.
Read the full abstract

Sound

Tracing a Sparse Emotion-Control Circuit in LLM-Based Text-to-Speech

Hongfei Du, Jiacheng Shi, Yanfu Zhang et al. (+1 more)

LLM-based text-to-speech (TTS) models can generate emotionally expressive speech, but how reference emotion is routed through the model and realized in decoded speech remains unclear. We introduce two emotion-sensitive metrics for matched neutral and emotional syntheses—a codec trajectory score and a late residual direction score—and use them to score activation-patching interventions. Under controlled matched-reference conditions, this analysis identifies a sparse source-to-readout component-level circuit: 23–27 attention heads and MLPs per emotion, roughly 5% of the components considered, recover or suppress 74–88% of the late emotion-readout shift on held-out cases. The circuit combines a shared component backbone with emotion-specific components; cross-emotion activation swaps reduce the target readout in 47 of 48 cases. In decoded speech, the same intervention produces consistent changes in pitch, energy, and spectral brightness over 24 matched pairs per emotion. A readout-matched residual-direction baseline produces only 17–27% of the intervention's pitch effect, showing that internal readout movement alone does not explain the decoded acoustic changes. These results trace a compact causal route from reference-derived prefix information to emotion-relevant properties of generated speech.
Read the full abstract

All authors Hongfei Du, Jiacheng Shi, Yanfu Zhang, Ye Gao

Sound · Cross-listed from cs.CL

AraYoungVoices: A Diverse L1/L2 Corpus of Arabic Child and Adolescent Speech

Shammur Absar Chowdhury, Zien Sheikh Ali, Houssam Eddine-Othman Lachemat et al. (+1 more)

State-of-the-art ASR systems primarily target native adult speech, leading to substantial performance gaps for children, adolescents, and L2 speakers. We introduce AraYoungVoices, a 151.72-hour Arabic read-speech corpus from 286 speakers aged 7–18, comprising AraKids (7–12) and AraTeens (13–18). The corpus includes 146 native Arabic (L1) and 140 second-language (L2) speakers, with native speakers spanning Egyptian, Gulf, Levantine, and North African dialectal backgrounds and L2 speakers representing diverse linguistic backgrounds across the Americas, Asia, Africa, and Europe. We benchmark four pretrained ASR models under zero-shot and fine-tuned settings using unseen-speaker-$\&$-unseen-prompt (USUP) and unseen-speaker-$\&$-seen-prompt (USSP) evaluations. Results show that L2 speech remains substantially more challenging than L1 speech, with the largest errors observed mainly for younger L2 speakers. Age-specific fine-tuning improves the matched age group, while joint fine-tuning provides a stronger balance across populations. ASR hypotheses are also consistently closer to the standard reading prompt than to the verbatim transcription, particularly for L2 speech, suggesting partial normalization of reading deviations.
Read the full abstract

All authors Shammur Absar Chowdhury, Zien Sheikh Ali, Houssam Eddine-Othman Lachemat, Hamdy Mubarak

Sound

TS-SP: Learning Speaker-Preserving Representations in Audio Large Language Models

Junjie Li, Zheng Liang, Zhe Li et al. (+2 more)

Audio large language models (ALLMs) can understand speech content, yet their ability to use speaker identity for verification remains limited. We propose TS-SP (Two-Stage Speaker Preservation), a parameter-efficient framework for learning speaker-preserving representations and making them accessible to an ALLM's language-model component. We instantiate and evaluate TS-SP on Qwen2.5-Omni-7B. First, we adapt the audio encoder with speaker identity supervision. We then freeze the adapted encoder and train the language model to compare speakers. Both stages use low-rank adaptation (LoRA), keeping the pretrained base weights fixed. On Vox1-O, TS-SP reduces the equal error rate (EER) from 7.01% for the Paired Loss Adaptation Baseline to 4.37%. EER remains within 4.31–4.79% under unseen prompts. Cross-domain evaluation on CN-Celeb yields a similar EER to the baseline, but lower accuracy at the native decision threshold. These findings support two-stage adaptation for improving speaker verification on the evaluated backbone.
Read the full abstract

All authors Junjie Li, Zheng Liang, Zhe Li, Tianchi Liu, Kong Aik Lee

Sound

A Multidimensional Model for Quantifying Tonal Strength: A Continuous Framework of Analyzing Tonal Evolution Beyond Tonal-Atonal Binary Classification

Yuliang Li, Nan Nan, Meilian Gu et al. (+1 more)

Tonality is a fundamental organizing principle of Western music. However, the gradual transition from common-practice tonality to atonality around the turn of the twentieth century cannot be captured by binary labels. To characterize intermediate tonal states and trace this evolution, we propose a multidimensional framework for quantifying tonal strength, grounded in tonal theory and mechanisms underlying tonal dissolution. This framework operationalizes the global statistical regularity, temporal coherence, and local perceptual alignment of tonal organization through three complementary features: pitch-class distribution uniformity, temporal stability of tonal centers, and local tonal clarity, respectively. To validate the model, we introduce two new datasets: a binary dataset comprising 196 tonal and atonal pieces, and a historical MIDI corpus of 1,561 compositions by 21 composers spanning the Baroque era to the early twentieth century. The proposed model achieves high discriminative performance on the binary classification task (F_1=0.985), and quantitatively reveals a continuous historical trajectory from established tonality through progressive weakening to eventual dissolution. Computational analysis of representative composers further confirms significant declines in tonal strength throughout the careers of late-Romantic and modernist figures. Additionally, analysis of EMOPIA dataset reveals a weak but statistically significant positive correlation between higher tonal strength values and positive emotional valence. This work establishes a unified quantitative model for analyzing tonal evolution and provides a continuous measure for future behavioral and neurophysiological investigations of the relationships among tonal organization, musical emotion, and cognition.
Read the full abstract

All authors Yuliang Li, Nan Nan, Meilian Gu, Xiaohong Guan

Sound

EchoChat: Structured Cognitive Reasoning in Empathetic Spoken Dialogue

Dingdong Wang, Shujie Liu, Yayue Deng et al. (+6 more)

Empathetic spoken dialogue is a sophisticated cognitive process that requires not only recognizing emotions but also inferring a user's latent mental states to provide appropriate support. However, current SpeechLLMs often treat empathy as a direct input-to-response mapping, leading to "superficially warm" but emotionally hollow interactions. In addition, since empathy relies on a multi-stage process with strong inter-step dependency, errors at any intermediate step can cascade through subsequent steps and lead to inappropriate responses, while existing training paradigms lack mechanisms to precisely localize and improve such errors. In this work, we propose EchoChat, a unified framework that reformulates empathetic spoken dialogue as a structured cognitive reasoning process integrating perception, mental-state reasoning, and response generation. To support this paradigm, we first construct EchoDialogue-400K, an acoustically rich dataset for multi-stage empathetic supervision. During the SFT stage, we strengthen acoustic grounding through proposed Acoustic-Anchored Attention (AAA). During the RL stage, we further introduce a novel stage-aware optimization objective with Step-Decomposed Credit Assignment (SDCA) to localize reasoning errors and mitigate cascaded error propagation. In addition, we introduce EchoEval, an expert-annotated benchmark for multi-dimensional empathy evaluation. Extensive experiments demonstrate that EchoChat achieves state-of-the-art performance in perception, reasoning, and response alignment. Project page: https://github.com/dingdongwang/EchoChat
Read the full abstract

All authors Dingdong Wang, Shujie Liu, Yayue Deng, Yuxuan Hu, Yunrui Cai, Jincenzi Wu, Jianwei Yu, Jinyu Li, Helen Meng

Saturday 3 October

Sound · Cross-listed from cs.CL

WavePrune: One period is often enough for RoPE

Guancheng Du, Luotian Huang, Shaowen Wang et al. (+2 more)

Rotary Position Embedding (RoPE) encodes token positions by rotating each two-dimensional channel of the query and key vectors at a channel-specific frequency, making the attention logits invariant to a common shift of positions. However, this rotation is periodic, and it leads to position aliasing where relative positions separated by a full rotation period become hard to tell apart. To address this, we propose WavePrune, which restricts each channel to its first rotation period. We show that it removes the distractions in attention maps created by position aliasing and improves overall long-context performance. Specifically, WavePrune raises the HELMET score on four of five models we test without any extra tuning (e.g., 35.7 -> 40.0 on Qwen3-8B). When pretraining models from scratch, WavePrune also achieves lower validation loss at extrapolated lengths than pretraining without it. Because WavePrune restricts each channel to a sliding window, it induces a fine-grained sparsity that our hardware-aligned CUDA kernels exploit for 1.15x prefill and 1.24x decoding speedups over FlashAttention-2 at 32K context. Together, these results show that RoPE's periodic structure, widely regarded as essential, is largely redundant beyond the first rotation period.
Read the full abstract

All authors Guancheng Du, Luotian Huang, Shaowen Wang, Si Li, Kaifeng Lyu

Sound · Cross-listed from cs.CL

EMODE: Dynamic Para-Semantic Experts for Emotion-Aware Speech Language Modeling

Jianan Pan, Yiwen Gu, Xinze Li et al. (+2 more)

Large speech language models have demonstrated strong capabilities in unified cross-modal understanding and generation, yet paralinguistic cues, especially emotion, remain difficult to preserve. Existing systems typically rely on entangled acoustic representations, which allow the underlying language model to depend excessively on recovered lexical content instead of grounding its behavior in acoustic-prosodic evidence. We address this limitation with EMODE, an emotion-aware speech language model built around Dynamic Para-Semantic Experts (DPSE). DPSE decomposes continuous speech features into semantic and paralinguistic pathways, routes them dynamically, and fuses them before integration into the language model. To turn this structural decomposition into functional specialization, EMODE is trained with a three-stage curriculum consisting of semantic warm-up, paralinguistic activation, and joint refinement, guided by Orthogonal Expert Guidance (OEG), Semantic-to-Acoustic Alignment (SAA), and Gating Diversity Regularization (GDR). Experiments on SER test, empathetic response evaluation, and the newly constructed bilingual MEPA benchmark show that EMODE improves the balance between lexical fidelity and emotional sensitivity, strengthens affect-grounded response generation, and exposes the value of explicit para-semantic factorization for robust cross-corpus emotion understanding.
Read the full abstract

All authors Jianan Pan, Yiwen Gu, Xinze Li, Rui Wang, Kejie Huang