Daily Papers — 2026-09-04

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

1. Tracing Audio Grounding and Answer Selection in Audio LLMs

Authors: Hyebin Cho, Suho Yoo, Jihoo Jung, Joon Son Chung

Categories: cs.CL, cs.AI, cs.LG, cs.SD | Preprint

Audio Large Language Models (Audio LLMs) have advanced in audio understanding, yet they can still predict the answer by reasoning from textual cues or linguistic priors rather than the provided audio. A common remedy is to train models on data whose answers cannot be inferred from text alone. This approach can improve performance, but what changes within the model remains unclear. In this paper, we ask what must happen inside the model for the audio to actually determine the answer. Our findings are threefold. (1) Replacing the audio with silence or unrelated audio causes substantially larger performance degradation in the trained model than in the pretrained model. (2) Acoustic information most strongly shapes the model’s representations of the answer choices in early-to-middle layers, while training mainly increases the influence of audio information on the final prediction in middle-to-late layers. (3) The weights learned during training have their largest impact in specific layer bands. Together, these results provide a mechanistic account of how training strengthens the use of acoustic evidence in Audio LLMs.

2. Sound-based Multi-Person 3D Pose Estimation

Authors: Yusuke Oumi, Yuto Shibata, Go Irie, Akisato Kimura, Yoshimitsu Aoki et al.

Categories: cs.CV, cs.AI, cs.LG, cs.RO, cs.SD | Accepted at ECCV 2026, Project Page: https://oumi03.github.io/sound-mhpe/

Can we recover the 3D poses of multiple people using only sound? This paper presents the first attempt to estimate multi-person 3D poses solely from acoustic signals. Estimating the poses of multiple individuals using acoustic signals is inherently challenging due to the superposition of motion-dependent signal variations. Unlike single-person scenarios, the presence of multiple subjects leads to overlapping acoustic signatures, making it difficult to attribute specific signal changes to an individual’s pose. Furthermore, the complexity is compounded by inter-person reflections, which introduce intricate propagation delays that obscure the temporal motion-acoustic relationship. To address these issues, we propose SoundMHPE (Sound-based Multi-person Human Pose Estimator), a novel encoder-decoder framework consisting of two key components. First, the Acoustic Multi-scale Encoder captures diverse temporal and fine-grained frequency features to isolate subtle acoustic signatures from complex, overlapping signals. Second, the Temporal Pose Decoder employs an attention mechanism to disentangle multi-person information across successive frames. By jointly accounting for temporal dynamics and inter-person dependencies, this component precisely reconstructs frame-wise individual poses. To validate our approach, we constructed the 6-hour Acoustic Multi-person Pose (AMP) dataset consisting of 432K synchronized frames of multi-person pose and acoustic data, and demonstrated that our SoundMHPE outperforms baseline models. Project page: https://oumi03.github.io/sound-mhpe/

3. PRISM-Bench: An Audio-Centric Diagnostic Benchmark for Text-to-Audio-Video Generation

Authors: Yuchen Sun, Qian Yang, Jun Wang, Detai Xin, Guoqiao Yu et al.

Categories: cs.MM, cs.AI, cs.SD | 19 pages, 10 figures, 4 tables. Accepted at ACM Multimedia 2026 (MM ‘26). This arXiv version includes supplementary appendices not included in the conference proceedings version

Text-to-audio-video (T2AV) generation has advanced rapidly, but its evaluation still underestimates the audio modality. Existing benchmarks either treat audio as an auxiliary component of video quality or assess it in isolation from audiovisual grounding, making it difficult to diagnose where current systems truly succeed or fail in audio generation. We present PRISM-Bench, the first audio-centric diagnostic benchmark for T2AV generation. Built from a rigorously curated dataset of 900 human-verified samples, PRISM-Bench factorizes audio evaluation along two orthogonal axes: audio type (Speech, Music, and Sound) and sound-source visibility (On-screen vs. Off-screen). It evaluates generated content across four perceptual dimensions (Audio-Visual Coherence, Audio Quality, Audio Expressiveness, and Prompt Following) with 35 fine-grained criteria. To ensure reliable assessment, we adopt an enhanced MLLM-as-a-Judge protocol based on blind, side-by-side comparison against ground-truth references, demonstrating strong alignment (over 70% mean agreement) with human raters. Our evaluation of recent T2AV systems highlights a significant performance gap between frontier and open-source models. Furthermore, we demonstrate that current generation paradigms overfit to perceptual fidelity while struggling with complex grounding and control tasks, particularly in generating music and synchronized On-screen audio.

4. Harmonica: Accurate and Lightweight Instrument-Agnostic Music Transcription

Authors: Longshen Ou, Héctor Martel, Joe Hennessy-Priest, Taemin Cho

Categories: cs.SD | Submitted to ICASSP 2027

This paper introduces Harmonica, a family of instrument-agnostic music transcription models built around multi-depth harmonic convolution. At each model scale, Harmonica achieves the best performance among the evaluated models: the x-large model attains state-of-the-art performance in instrument-agnostic transcription, while the medium variant offers competitive accuracy with faster inference than all baselines. Pushing the limit of computational efficiency, the nano variant has only 26.3K parameters and runs at 1,622.5 times real time, yet achieves a frame F1 of 0.796 on the development set, 14.6 percentage points higher than Basic Pitch. We further demonstrate that multi-depth harmonic convolution effectively exploits harmonic information to benefit transcription performance through comparative experiments with existing harmonic aggregation methods, including harmonic stacking, harmonic attention, single-depth harmonic convolution, and the HD-Conv layer.

5. KanAdapter: A Kolmogorov-Arnold Network-based Plug-and-Play Module for Efficient Fine-tuning of Foundation Speech Models

Authors: Phuong Tuan Dat, Phuong Khai Minh, Tran Huy Dat

Categories: cs.SD | Accepted to IMPACT-SPEECH Workshop @ EMNLP 2026

Fully fine-tuning self-supervised learning (SSL) speech models for downstream tasks is computationally prohibitive, and existing parameter-efficient fine-tuning approaches predominantly rely on MLP-based adapters whose fixed activation functions limit their representational expressiveness under tight parameter budgets. We propose \textbf{KanAdapter}, a lightweight adapter framework that replaces conventional MLP bottlenecks with Group-Rational Kolmogorov-Arnold Network (GR-KAN) modules for more expressive and parameter-efficient adaptation. Following a parallel bottleneck design, KanAdapter inserts trainable GR-KAN branches alongside frozen Transformer encoder blocks and leverages weight transfer from pre-trained MLP layers for stable initialization. Across speaker verification, speech emotion recognition, and deepfake detection, KanAdapter achieves up to 97.5\% reduction in trainable parameters relative to full fine-tuning while remaining highly competitive, and consistently outperforms AdaptFormer under comparable parameter budgets. In continual learning, it yields up to 83.6\% error reduction over full fine-tuning and MLP-based adapters, which we attribute to the localized nature of GR-KAN’s rational activations that mitigates catastrophic forgetting. To our knowledge, this is the first work to explore KAN-based modules for parameter-efficient fine-tuning of speech foundation models.

6. One-Stage Multi-Task Instruction-Guided 3D Spatial Audio Editing

Authors: Ke Lei, Chenyuhao Wen, Yu Zhang, Wenxiang Guo, Changhao Pan et al.

Categories: cs.SD

Spatial audio editing modifies an existing soundfield according to a user’s instruction while preserving the rest of the scene. Unlike conventional audio editing, it must reason jointly about audio events, spatial information, dynamic changes, and environmental information in first-order Ambisonic (FOA) waveforms. Existing language-guided editors mainly target conventional audio or rely on sequential operations, and therefore do not directly support one-stage editing for complex 3D spatial instructions. We present SwanWeave, the first one-stage multi-task framework for instruction-guided 3D FOA spatial audio editing. We build paired FOA supervision from open-source speech and sound-effect corpora using controllable room simulation, covering more than ten single-operation and compound tasks across the four editing axes. To handle this heterogeneous edit space, SwanWeave uses Spatial Edit Mixture-of-Experts (SE-MoE) with dual-level routing, selecting task-aware expert combinations for compound instructions and frame-level routed/null experts for local edit decisions. We further introduce Spatial Preference Optimization (SPO), a Direct Preference Optimization (DPO)-based alignment objective with edit-specific negative targets, and adopt staged training to improve natural-language grounding. Experiments show that SwanWeave achieves better editing quality than existing general audio editors and spatial audio baselines across all tasks. Spatial audio editing demos can be found at https://swanaigc.github.io/#swanweave, code can be found at: https://github.com/MM-Speech/SwanWeave.

7. ProLombard: Structured Multi-Scale Modeling for Normal-to-Lombard Speech Conversion

Authors: Hongyang Chen, Xinmeng Xu, Youqiang Zheng, Xingyu Liu, Yuhong Yang et al.

Categories: cs.SD | Submitted to IEEE/ACM Transactions on Audio, Speech, and Language Processing

Normal-to-Lombard (N2L) speech conversion aims to improve speech intelligibility in noisy environments by transforming normal speech into Lombard-style speech while preserving linguistic content, speaker identity, and speech quality. Despite recent progress, existing methods typically model the Lombard effect at the utterance level or the frame level, overlooking its hierarchical nature and its entanglement with both speaker identity and phoneme-level content. This limitation leads to Lombard leakage in speaker representations and incomplete separation between Lombard characteristics and linguistic content. In this work, we propose ProLombard, a structured multi-scale N2L framework that explicitly models the Lombard effect across utterance-, phoneme-, and frame-level representations. To address Lombard-speaker entanglement, we introduce an aligned speaker encoder (ASE) that suppresses Lombard leakage by aligning Lombard-speech speaker embeddings with their normal-speech counterparts. To achieve more complete Lombard-content disentanglement, we develop a phoneme-aware disentanglement and injection mechanism that extends conventional frame-level modeling to the phoneme level. Furthermore, we design a vector quantization (VQ)-median module that provides robust phoneme-level representations through VQ-based segmentation and median-frame-based aggregation. Extensive experiments on Mandarin and English Lombard datasets demonstrate that the proposed approach consistently improves speech intelligibility, Lombard similarity, and perceptual quality over baselines while maintaining speaker identity. These results highlight the importance of structured multi-scale modeling for effective N2L speech conversion.

8. What Did I Just Say? Self-Listening for Full-Duplex Speech Models

Authors: Xuanning Zhou, Junyi Ao, Xiaotong Liu, Tom Ko, Benyou Wang et al.

Categories: cs.SD

Full-duplex spoken language models can listen and speak simultaneously, enabling them to handle interruptions and backchannels in human conversation. However, text generation, speech synthesis, and audio playback proceed asynchronously. As a result, what a model believes it has said may not match what has actually been played to the user. We refer to the problem of recovering from an interruption while remaining aware of the model’s realized speech as anchor interruption. To address this problem, we propose Self-Listening, a full-duplex modeling approach that interleaves user speech, model text, and the model’s played speech. By feeding the realized speech output back to the model as an input stream, self-listening grounds interruption recovery in what the user has actually heard. We further introduce AnchorSpeech, a collection with homogeneous training and test splits for tracking which items of structured ordered responses have actually been spoken. AnchorSpeech-test evaluates whether a model can respond consistently with the last completed item before an interruption. Experiments show that, compared with full-duplex baselines, models equipped with self-listening mechanism achieve better anchoring performance.

9. SCAPES: Semantically Conditioned Autoregressive Prior for Environmental Sounds

Authors: Esteban Gutiérrez, Lonce Wyse, Frederic Font, Xavier Serra

Categories: cs.SD, cs.AI, cs.LG | Accepted to the Digital Audio Fx (DAFx) Conference 2026 to be held in Cambridge, USA. 8 pages, 3 figures and 2 tables

As generative audio models grow in complexity, the computational and ecological costs of synthesizing everyday sounds have become increasingly prohibitive, often requiring industrial-scale resources and massive datasets. In this paper, we present SCAPES: a Semantically Conditioned Autoregressive Prior for Environmental Sounds. SCAPES is a lightweight, resource-efficient generative model designed to synthesize high-fidelity environmental textures through high-level semantic control. By operating on the continuous latent manifold of a neural audio codec, our approach bypasses the rigid structural constraints inherent to discrete tokenization. We propose a segmentation strategy that decomposes audio into overlapping segments, enabling a Continuous Normalizing Flow (CNF) to model the evolution of latent trajectories using Flow Matching. Our experiments demonstrate that a 36-million parameter instance of SCAPES can be trained on limited, uncurated datasets using a single consumer-grade GPU. Notably, convergence is achieved after training for approximately twice the source audio duration, yielding high-fidelity outputs with robust long-term stability and semantic consistency. Furthermore, we showcase the model’s capacity for smooth semantic interpolation, providing a flexible and accessible tool for open research and creative sound design. Code, pretrained weights, audio examples, and an interactive demo are publicly available on our project page https://cordutie.github.io/projects/scapes.html

10. Emotion as a Distribution: Joint Valence-Arousal Probability Learning for Speaker-Independent Multimodal Emotion Recognition

Authors: Tingyi Lin, Wen-Ren Yang, Kuanwei Chen

Categories: cs.SD, cs.CL | 18 pages, 8 figures. Submitted to Speech Communication. Code: https://github.com/brian10420/EchoMind-Mamba-VA-SER (archived: doi:10.5281/zenodo.21904810)

Human emotion is graded and frequently mixed, yet most multimodal recognizers collapse it onto a single hard label. We argue the recognizer should instead expose a distribution over affective space. Our text+speech system, alongside its categorical decision, emits a $9\times9$ probability matrix over the Valence-Arousal plane, trained with a two-dimensional Gaussian soft target under a Kullback-Leibler/cross-entropy objective, aimed at counseling support. Evaluation is strict: speaker-independent 5-fold leave-one-session-out IEMOCAP with rotating-session inner validation, headline metrics only on the held-out session. Within one fixed encoder-fusion-head pipeline we compare Transformer and state-space (Mamba-1/2/3) backbones at matched depth and width, at two operating points ($T\approx550$, $T\approx2750$). The featured dual-head system reaches 73.0% $\pm$ 0.3 unweighted accuracy over three seeds (separate rerun: 72.1%), exceeding the Transformer fusion baseline by 3.0 UA points (95% session-bootstrap CI [1.0,4.7]; significant under paired t-test and session-level bootstrap), with no latency or memory advantage at these lengths; swapping the ~1M trainable front-end for frozen WavLM-Large features (learnable layer weights) lifts the same architecture to 76.6% $\pm$ 1.3. Pre-specified controls scope the claims honestly: simpler valence-arousal auxiliaries reproduce the classification lift within noise, and a dedicated regression head tracks the continuous ratings slightly better, so the head’s specific value is the normalized affect distribution itself. That distribution recovers the circumplex: its center of mass tracks valence and arousal (CCC 0.66/0.66; predominantly between-class structure, weaker within-class tracking), and its entropy is weakly but consistently linked to categorical rater ambiguity, not dimensional spread.

11. Enhancing Neural Speech Coding with Semantic and Visual Cues

Authors: Yao Guo, Yang Ai, Hui-Peng Du, Xiao-Hang Jiang, Chen-Yuan Ning et al.

Categories: eess.AS | 6 pages, 2 figures, submitted to APSIPA 2026

At low bitrates, neural speech codecs have limited capacity to encode all information needed for high-quality re construction, especially when relying solely on speech-derived representations. To address this limitation, this paper proposes a Semantic- and Visual-enhanced Speech Codec (SVSC), which in corporates semantic and visual cues into the neural speech coding process. Specifically, built upon a mainstream neural speech cod ing architecture, SVSC introduces a semantic encoding-decoding branch and an image analysis-synthesis branch. It fuses deep semantic features with visual cues through a cross-attention mech anism, forming an auxiliary high-level representation enriched with contextual and articulatory information. To handle different inference scenarios, SVSC introduces two information-injection strategies based on the availability of auxiliary semantic and vi sual cues. When such cues are available, the fusion mode directly incorporates the auxiliary representations into the speech coding branch through feature concatenation; otherwise, the distillation mode transfers auxiliary information into the speech coding branch through knowledge distillation during training, enabling speech-only inference without additional inputs. Experimental results validate the effectiveness of incorporating semantic and visual cues, improving the ViSQOL score of reconstructed speech from 3.86 to 4.01.

12. MedWER: A Reproducible, Model-Free Evaluation Protocol for Medical Speech Recognition

Authors: Justin Behling

Categories: cs.CL | 10 pages, 3 tables. Code, term list, and evaluation scripts: https://github.com/Nordis-Tech/medwer. Package: pip install medwer. Source archive: https://doi.org/10.5281/zenodo.22103865

Overall word error rate hides clinically critical errors: a transcript can be 95% correct and still swap one drug for another. The usual fix weights errors on medical entities, and almost always depends on an evaluation-time named-entity recognition (NER) model or cloud API, which makes the metric’s denominator a versioned black box. We present MedWER, an evaluation protocol and open-source tool for medical ASR whose denominator is a fixed, license-clean term list: 19,373 drug, diagnosis, symptom, and injury-mechanism entries projected from public sources. The protocol couples a pinned text normalizer with a phrase-aware term-restricted WER, the MedWER, so the only versioned component is a normalizer dependency held at an exact release and checked against committed golden fixtures. Coverage is validated against an independent provincial drug-benefit file the list was not built from; the matching heuristic is calibrated against ground-truth entity spans. Baselines for Moonshine~base, Whisper~base.en, and MedASR on two open benchmarks are scored with the released tool and reported with 95% confidence intervals from resampled per-utterance scores.

13. InterSing: Explicit Interaction Dynamics for 3D Duet Singing Animation and Beyond

Authors: Yihan Zhou, Zikai Huang, Yuyang Yu, Xuemiao Xu, Cheng Xu et al.

Categories: cs.CV

We present InterSing, a framework for generating realistic 3D head animations for duet singing performances. Unlike solo singing, duet performance requires each singer to balance individual expressiveness with intermittent interaction at musically salient moments, such as phrase boundaries, synchronized rhythms, and call-and-response passages. Because these interactions are sparse and rhythm-dependent, existing audio-driven animation methods and conversational interaction models do not adequately capture their structure. Our key insight is that duet coordination can be represented as a time-varying signal that reflects how strongly performers engage with one another throughout a song. Based on this observation, we introduce interaction logits, an interpretable latent representation that models the degree of cross-performer engagement at each time step. We learn these logits using weak supervision and use them to condition an interaction-aware diffusion model jointly driven by audio features and interaction dynamics. This formulation enables unified multi-mode generation, spanning independent motion, coordinated behavior, and smooth transitions between them. Experiments show that InterSing generates realistic and expressive singing head animations with stronger coordination and musical alignment than existing methods, while preserving each performer’s characteristic motion style. We further demonstrate that the same formulation generalizes to multi-singer performances and provides intuitive control over when and how performers engage.

14. Full-Page Optical Music Recognition of Handwritten Monophonic Scores

Authors: Adrian Rosello, Antonio Ríos-Vila, David Rizo, Jorge Calvo-Zaragoza

Categories: cs.CV, cs.AI

Full-page end-to-end Optical Music Recognition seeks to transcribe entire music pages directly into symbolic notation, avoiding the limitations of traditional pipelines that rely on accurate staff segmentation. Recent Transformer-based architectures have achieved strong performance on typeset scores, relying on large-scale synthetic data for pretraining. However, their applicability to handwritten music remains largely unexplored. In this work, we study full-page transcription on handwritten monophonic collections and analyze the impact of synthetic pretraining in this setting. To investigate which factors are most relevant during pretraining, we introduce a generator capable of producing visually coherent full-page scores in both typeset and handwritten styles. Experiments on three real handwritten datasets provide a comparative evaluation of several full-page pipelines and different synthetic pretraining strategies. The results suggest that the benefits of synthetic pretraining are primarily associated with learning structural layout conventions rather than with visual similarity to the target handwriting.