Daily Papers — 2026-09-07

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

1. RAFM-SER++: A Lightweight Multimodal Emotion Recognition Framework for Real-Time Behavioral Monitoring in Surveillance Systems

Authors: Ngo Truong Dinh, Tung-Lam Bui, Chi-Trung Duong, Vien Nguyen Thi, Viet-Anh Nguyen et al.

Categories: cs.AI, cs.LG, cs.MM, cs.SD | 6 pages, 4 figures, 3 tables. Accepted at the 2026 IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS 2026). (c) 2026 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

Recent multimodal Speech Emotion Recognition (SER) systems achieve high accuracy through interaction-heavy cross-modal transformers, but their computational cost limits deployment in latency-sensitive and resource-constrained surveillance systems. To address this challenge, we propose RAFM_SER++, a lightweight multimodal SER framework featuring an asymmetric Residual Attention Fusion Mechanism (RAFM). Rather than relying on computationally expensive bidirectional interactions, RAFM injects affective speech cues into semantic text representations through a one-directional residual attention pathway. Combined with a BYOL-inspired cross-modal alignment objective and attention-guided pooling, the proposed framework improves multimodal representation learning while maintaining low computational overhead. Experiments on the IEMOCAP and ESD benchmarks demonstrate that RAFM_SER++ consistently outperforms the HuBERT-Base baseline and achieves a superior accuracy-efficiency trade-off compared with the state-of-the-art MemoCMT. Specifically, RAFM_SER++ reduces trainable parameters by more than 60%, achieves faster inference (79.60 it/s), and attains BACC scores of 81.10% on IEMOCAP and 95.39% on ESD. These results indicate that lightweight asymmetric multimodal fusion is an effective alternative to interaction-heavy cross-modal transformers for real-time surveillance applications.

2. AdoDAS: A Privacy-Preserving Multimodal Challenge for Adolescent Depression, Anxiety, and Stress Assessment

Authors: Zhaojie Luo, Junkun Wang, Tianhua Qi, Yuxuan Wu, Xin Zhao et al.

Categories: cs.MM, cs.SD | 5 pages, 1 figure, 3 tables. To appear in the Proceedings of the 34th ACM International Conference on Multimedia (MM ‘26), November 10-14, 2026, Rio de Janeiro, Brazil. Zhaojie Luo and Junkun Wang contributed equally

Adolescent depression, anxiety, and stress (D/A/S) call for scalable tools that complement, rather than replace, professional evaluation. Under a privacy-preserving policy, the AdoDAS Grand Challenge withholds minors’ raw recordings and distributes anonymized audio-visual representations and ASR-derived text. Its 6,000 participants provide 24,000 segments across one scripted-reading and three open-response sessions. Two tracks assess multi-task binary D/A/S screening and ordinal prediction of 21 DASS-21 item responses. From 191 registrations, the final leaderboards included 95 eligible screening teams and 64 item-prediction teams. Audio-visual baselines achieved 0.4604 mean F1 and 0.2675 mean Quadratic Weighted Kappa; leading submissions reached 0.5921 and 0.2776. Representative systems emphasize cross-session modelling, temporal multimodal fusion, psychometric structure, and task-aware calibration.

3. Geometry-Informed Distributed Acoustic Scene Understanding

Authors: Yiyuan Yang, Shitong Xu, Niki Trigoni, Andrew Markham

Categories: cs.SD | Accepted by Interspeech 2026 Conference

Acoustic scene understanding in multi-room environments is a difficult task. Most existing systems use a single centralized microphone array, and they often fail because walls and doors block sound signals. To address this challenge, we propose a geometry-informed distributed acoustic scene understanding framework. Our system leverages distributed microphones and uses an audio spectrogram transformer and a topology-aware graph neural network to fuse spatio-temporal acoustic features. Then, these features are decoded into discrete semantic triplets. Finally, a frozen large language model combines these symbolic observations with the environmental geometry. This allows the system to perform spatial understanding, infer plausible missing transitions, and generate a physically consistent narrative of the scene. Experiments on a custom multi-room simulator demonstrate that our framework outperforms centralized baselines and improves spatial consistency under simulated occlusion.

4. Silent Metronome: Rhythmic Grounding for Live Music Accompaniment

Authors: Kevin Bretz, Derya Soydaner, Aske Plaat

Categories: cs.SD | 5 pages, 2 figures, 1 table

Live accompaniment models generate music for an incoming audio stream, committing to each output frame before hearing what comes next. In this strictly causal setting the model must infer tempo, meter, and metrical phase from its own imperfect past, whereby compounding errors quickly become audible as rhythmic drift. Put simply, the model has ears but no temporal reference, so when the ears hear imperfect, ambiguous music, the model will produce a flawed output. We propose Silent Metronome (SiMe), which gives it the temporal reference, encoding the phase within the beat and within the bar as periodic functions, pairing them with tempo and time signature, and supplying the result as a separate conditioning channel. Because this reference is independent of the generated audio, it cannot drift. Complementary auxiliary heads shape the latent representation, including a novel head that predicts the model’s own future tokens. With the metrical signal taken from ground-truth annotations, beat alignment improves by a factor of 3.2 over the strictly causal baseline and surpasses a non-causal reference granted a full second of look-ahead. Coherence between input and accompaniment stays within a single point of that reference. These results suggest that streaming accompaniment systems should treat rhythm as a signal to be shared, as human ensembles do, rather than inferred.

5. Frequency Estimation Based on SNR-adaptive Frequency Estimator Under Wide SNR Range

Authors: Hee-Yang Jung, Dong-Hee Paek, Woo-Jin Jung, Seung-Hyun Kong

Categories: cs.SD, cs.AI | 10 pages, 6 figures

Frequency estimation is the problem of estimating individual tone frequencies from noisy multi-tone sinusoidal signals. Existing frequency estimation methods have difficulty accurately estimating both the number of tone frequencies and the individual tone frequencies in low signal-to-noise ratio (SNR) environments, because weak tone frequency components are buried in noise. In addition, existing methods generally exhibit a trade-off between robustness at low SNR and frequency estimation precision at high SNR, making it difficult to achieve consistently superior frequency estimation performance over a wide SNR range. To overcome these limitations, this paper proposes an SNR-adaptive frequency estimator (SAFE). SAFE consists of a time-frequency image neural network (TFINet), which enhances weak tone frequency components at low SNR, and an SNR-based frequency selector (SFS), which selects an appropriate frequency estimator according to the SNR of the estimated tone frequencies. TFINet enhances tone frequency components even in the low-SNR range, while SFS estimates the SNR of each tone frequency and selects either a robust frequency estimator or a super-resolution frequency estimator according to the estimated SNR. This enables SAFE to achieve robustness at low SNR while preserving high precision at high SNR. Simulation results show that SAFE achieves an False Negative Rate (FNR) of 13.00% over the SNR range from -10 dB to 0 dB, corresponding to an 13.04% improvement over the state-of-the-art method. In addition, SAFE reduces the Nearest Neighbor-Root Mean Squared Error (NN-RMSE) by 56.67% compared with the state-of-the-art method, demonstrating that SAFE performs more accurate frequency estimation. Furthermore, experiments using real-world data demonstrate that SAFE provides robust frequency estimation performance even in practical environments with clutter.

6. Comparing Self-Supervised and Domain-Invariant Features for Cross-Domain Voice Phishing Detection

Authors: Jeongmin Lee, Seung Yun, Minkyu Lee, Ran Han, Yoonkyu Woo et al.

Categories: cs.SD, cs.CL | 5 pages, 2 figures. Accepted at INTERSPEECH 2026

Voice phishing detection faces three critical challenges: real criminal recordings are unavailable due to privacy constraints; when available, only a handful of samples exist, insufficient for fine-tuning; and lightweight acoustic-only detection is needed as an alternative to large self-supervised models. We compare domain-invariant prosodic features and self-supervised representations (HuBERT, wav2vec2.0) through cross-domain evaluation-training on scenario-based actor recordings and testing on authentic criminal calls. Domain-invariant prosodic features achieve 69.5% F1 zero-shot and 71.0% with 5-shot learning. HuBERT achieves highest performance (94.2% F1, 5-shot), while wav2vec2.0 exhibits a precision-oriented detection profile (90.2% F1 with 99.4% precision, 5-shot). These findings reveal fundamental trade-offs: domain-invariant features enable zero-shot deployment when no real data exists, while SSL methods achieve higher performance but require real samples and compute.

7. KABURI-TTS: Phoneme-Keyed Activity-conditioned Bi-channel Utterance Rendering for Interaction

Authors: Ryuichiro Higashinaka, Shinnosuke Takamichi, Tetsuji Ogawa

Categories: cs.SD, cs.CL | Accepted at APSIPA ASC 2026

Realizing full-duplex spoken dialogue requires large amounts of two-channel, one-speaker-per-channel conversational speech data. Although conversational text-to-speech (TTS) engines have been developed, they are not necessarily robust to two-party simultaneous phenomena such as backchannels, interruptions, and overlaps that occur while the interlocutor is speaking. In this work, aiming at conversational speech synthesis that reproduces human-like overlap, we propose KABURI-TTS. KABURI-TTS takes a per-speaker phoneme raster as input and renders the speech of the two speakers on separate channels, conditioned on the per-frame phonemes and the voice activity derived from them. Because the phoneme raster is supplied by a separate module, the proposed method enables controllable generation of one-speaker-per-channel, two-party spoken dialogue. A user evaluation shows that, compared with strong baselines, the proposed method attains higher naturalness at both the utterance and the interaction level. Furthermore, an analysis of voice activity confirms that the proposed method produces more overlap and more frequent turn-taking.

8. TAD: Token-Adaptive Contrastive Decoding with Confidence-Guided Gating for Hallucination Mitigation in Large Audio-Language Models

Authors: Heyu Chang, Nianwen Si, Hao Zhang, Wenlin Zhang, Dan Qu

Categories: cs.SD, cs.CL, cs.CV | Accepted to Interspeech 2026

Large audio-language models (LALMs) can hallucinate audio objects, answering “yes” to absent sound events, thus undermining reliability in audio question answering. We propose Token-Adaptive Decoding (TAD), a training-free strategy for hallucination mitigation that grounds the initial yes/no decision by contrasting logits under real audio with a matched silent reference. TAD introduces a token-adaptive, confidence-guided gate that is decision-critical at the first decoding step and class-conditional on affirmative tokens, using the audio-silent margin to avoid overcorrection when evidence is weak or already sufficient. Experiments on AudioCaps-Hallucination show that, relative to Audio-Aware Decoding (AAD), a contrastive baseline with fixed contrast strength, TAD improves F1 for Qwen2 by 0.059 to 0.117 across Popular, Adversarial, and Random splits, and for Gemma by 0.025 to 0.064, while on Clotho-AQA it raises F1 from 0.810 to 0.816 on Qwen2 and remains comparable to AAD on Gemma.

9. Clean Accuracy Does Not Guarantee Provenance Robustness: A Prospective Codec-Stress Evaluation of Audio Attribution

Authors: Gang Shi

Categories: cs.SD, cs.LG | 13 pages, 5 figures

Audio provenance attribution - which system produced a synthetic utterance - is reported at near-ceiling accuracy on clean benchmarks, yet audio reaching an analyst has usually been transcoded. We report a prospectively registered measurement of closed-set attribution after single-stage codec transport, with the analysis region fixed from fidelity metadata before any attribution model was trained. On two corpora, in-support losses reach 53.5 [43.5, 63.6] and 70.3 [63.0, 77.5] Macro-F1 points for WavLM-Base+, and 61.0 [56.8, 65.1] and 49.8 [41.6, 57.9] for W2V2-BERT 2.0, under simultaneous component-level bands. Degradation is strongly condition- and representation-dependent: within one in-support grid WavLM losses run from -0.4 to +53.5 points, and the two encoders differ beyond a prespecified +/-5-point margin at six of twelve conditions. A clean-qualified ECAPA-TDNN and a Proxy-Anchor head degrade comparably, so the effect is not confined to one representation family or a weak linear head. The registered matched-fidelity comparison was not estimable on this grid, and waveform and perceptual measures order the conditions differently: MP3 at 8 kbit/s ranks mid-grid on SI-SDR but last on PESQ-WB while causing the largest loss. For the tested tasks, corpora, representations and codec grid, a clean accuracy figure does not by itself characterise deployment robustness.

10. Iterative Audio Separation with Mixture Consistency via MIMO Model Extension

Authors: Yukara Ikemiya, WeiHsiang Liao, Yuki Mitsufuji

Categories: cs.SD, cs.LG

This paper proposes a general framework for stable and effective iterative audio separation with mixture consistency by extending source separation models to a multi-input multi-output (MIMO) configuration. In the field of audio separation, mixture consistency is an essential property for many applications that require accurate phase and timbral information of target sources. While iterative approaches such as diffusion models achieve perceptually superior results in speech enhancement or user-guided target source separation tasks, most existing methods focus on single-step separation with a single-input single-output (SISO) or single-input multi-output (SIMO) configuration through architectural improvements, since mixture-consistent audio separation is generally regarded as a regression problem that admits a unique solution. By extending these architectures to a MIMO configuration, we introduce iterative prediction without compromising the architectural advantages or the characteristics of mixture consistency. We conduct a comprehensive ablation study of combining the framework with discriminators and extending it to a generative model. Experimental results demonstrate significant performance improvements when applying the proposed framework to state-of-the-art separation models.

11. Direction-Preserving Active Noise Control with a Conditional Control-Filter Estimation Network

Authors: Ziyi Yang, Zhengding Luo, Boxiang Wang, Libin Zhang, Woon-Seng Gan

Categories: eess.AS | 12 pages, 7 figures, 4 tables

Conventional active noise control (ANC) minimizes the total disturbance at the error microphone without distinguishing desired sound from noise. Direction-preserving ANC (DP-ANC) instead aims to attenuate a noise component arriving from a direction other than the specified desired direction while preserving sound naturally arriving from that direction. Existing approaches typically either require analytical optimization to be repeated for each new observation or estimate and reproduce the desired component through a hear-through secondary-source path. To address these limitations, this paper formulates DP-ANC as a direction-conditioned cancellation-preservation optimization problem. A component-separated objective jointly penalizes residual noise energy and the control response induced by the desired component, with a scalar weighting parameter controlling the cancellation-preservation trade-off. A convolutional network conditioned on the specified desired direction through feature-wise linear modulation (FiLM) is trained using a differentiable secondary-path-aware forward model. At deployment, the network estimates the complete multichannel finite impulse response (FIR) control-filter bank directly from a mixed-reference observation and the specified desired direction in a single forward pass, while retaining the conventional feedforward ANC signal path. Over 3300 evaluation cases, the selected operating point achieves 22.8 dB mean noise reduction with a desired-signal distortion of -11.4 dB. Validation using measured in-ear-device transfer functions further demonstrates consistent performance under measured acoustic configurations.

12. A General Approach to Enharmonicism

Authors: Caleb Scott Alons

Categories: math.HO, cs.SD | 20 pages, 12 figures, 3 tables; submitted to the Journal of Mathematics and Music

We propose a general approach to enharmonicism within syntactic music theory; that is, we formalize several abstract structures of enharmonicism without any acoustic considerations. The structures of concern to this paper are constructed from diatonics, chromatics, and enharmonics, and we seek to present a general enharmonic theory that builds upon Hook’s enharmonic theory published in “Enharmonic Systems: A Theory of Key Signatures, Enharmonic Equivalence and Diatonicism” (2007). We also propose that the two criteria of reflection and maximal evenness can be used to determine whether an arbitrary enharmonic system is musically practical. Moreover, we argue that preferential treatment of the standard enharmonic system (SES) can be motivated from an abstract mathematical perspective divorced from pitch consideration and conventional acoustic constructions of SES.

13. Qwen-Audio-3.0-ASR Technical Report

Authors: Chuanmeng Bian, Daren Chen, Peixin Chen, Zhigao Chen, Zhiyun Fan et al.

Categories: cs.CL | 21 pages, 11 figures. Authors are listed in alphabetical order by surname

In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model scaling, and deep integration with large language models (LLMs). However, bridging the gap between academic benchmark performance and real-world production utility remains a persistent challenge, particularly in handling diverse regional dialects, dynamic entities and hotwords, long-range contextual information, and disfluent spontaneous speech. In this report, we present Qwen-Audio-3.0-ASR, a Mixture-of-Experts (MoE) LLM-based ASR system designed to address these production demands through a unified, instruction-following framework. The model is built upon the Qwen backbone, and is trained on tens of millions of hours of large-scale speech data. Qwen-Audio-3.0-ASR supports transcription across 30 languages and 16 Chinese dialectal varieties spanning eight major dialect regions. Beyond multilingual and dialectal recognition, the model provides production-oriented capabilities including industry-domain entity recognition, hierarchical hotword customization, native single-pass transcription polishing, and long-audio contextual modeling. We further develop a dedicated streaming variant, Qwen-Audio-3.0-ASR-Streaming, for latency-sensitive applications. Extensive evaluations on Chinese, English, multilingual, and real-world industrial test sets demonstrate state-of-the-art or highly competitive recognition performance across a broad range of evaluation conditions, with strong performance relative to leading commercial and proprietary systems including GPT-4o Transcribe and Gemini 3.1 Pro.

14. AV-SafetyBench: A Safety Benchmark for Text-to-Audio-Video Generation

Authors: Suah Choi, Tae-Young Lee, Gyeong-Moon Park

Categories: cs.CV, cs.AI | 34 pages, 19 figures, 17 tables

Recent text-to-audio-video (T2AV) models jointly generate video, speech, sound effects, and ambience from a single text prompt. This capability poses new challenges for safety evaluation, as unsafe content may be conveyed through the audio track or arise only when the visual and audio tracks are interpreted jointly. Existing safety benchmarks largely focus on either generated video or generated audio in isolation and are therefore not designed to capture these risks. To close this gap, we introduce AV-SafetyBench, the first safety benchmark developed specifically for T2AV generation. AV-SafetyBench comprises a four-axis, 13-category taxonomy and 5,200 manually reviewed prompts that specify visual scenes, speech, and non-speech audio. Our evaluation protocol assesses each output under three views: Full-AV, Video-Only, and Audio-Only. It then uses the Video-Only and Audio-Only judgments to assign Full-AV unsafe outputs to one of four risk sources: Video-Only, Audio-Only, AV-Both, or AV-Joint. We evaluate five open-source T2AV models and validate the automated Full-AV judgments against human annotations. Across the five models, Full-AV Unsafe Rates range from 25.1% to 49.4%. Beyond these aggregate rates, risk-source analysis reveals that, for four of the five models, Audio-Only and AV-Joint cases-unsafe outputs missed by video-only evaluation-account for 41.6-48.3% of Full-AV unsafe outputs for which a risk source could be assigned. In the Cross-Modal Harm Emergence category, AV-Joint accounts for 87.5% of unsafe outputs withan assigned risk source. Together, these findings demonstrate the value of AV-SafetyBench for evaluating T2AV safety across the visual and audio modalities and their interaction.

15. SeisBench DAS: A machine learning framework for Distributed Acoustic Sensing

Authors: Jannes Münchmeyer, Han Xiao, Frederik Tilmann

Categories: physics.geo-ph, cs.LG | 14 pages, 5 figures

Fibre optic sensing, such as distributed acoustic sensing (DAS), has become a widespread technology for geophysical studies. To process the large-scale datasets produced by DAS, several machine learning methods have been proposed. However, without standardization of data and models, these methods lack comparability and interoperability. This introduces a gap between model developers and practitioners analyzing DAS data and inhibits adoption of deep learning for DAS. To address these limitations, here we present SeisBench DAS, an extension to the SeisBench library for machine learning in seismology. SeisBench DAS defines standard formats for DAS benchmark datasets, including standardised metadata and labels, and DAS models. It builds on the xdas framework for data ingestion and virtual array handling, and on PyTorch for reading and applying the machine learning models. Importantly, SeisBench provides an engine to efficiently apply deep learning models to diverse formats of DAS data, bridging the gap between model developers and practitioners. SeisBench DAS is designed as an open and extensible framework, allowing to easily incorporate future developments in deep learning for DAS.