cs.SD · 2026-06-15 · No. 24

Sound, 2026-06-15.

7 new papers in cs.SD. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

7 entries
  1. 01

    Listening with Attention: Entropy-Guided Explainability for Transformer-Based Audio Models

    Ravi Ranjan, Utkarsh Grover, Xiaomin Lin, Agoritsa Polyzou

    cs.SD · cs.AI

    Transformer-based automatic speech recognition (ASR) models such as Whisper are highly accurate, but their predictions remain difficult to interpret. Existing explainable AI (XAI) methods often lack faithfulness and precise temporal grounding. We propose Listening with Entropy-guided Attention for Faithful explainability (LEAF-X), a model-intrinsic XAI framework for transformer-based ASR. LEAF-X combines entropy-guided attention weighting,...

    arxiv.org/abs/2606.14647 · PDF

  2. 02

    From Self-Supervised Speech Models to Mixture-of-Experts for Robust Anti-Spoofing

    Hugo Daumain, Driss Matrouf, Khaled Khelif, Mickael Rouvier

    cs.SD · cs.AI

    Recent advances in speech generation have significantly improved the naturalness of synthetic speech, making spoofing detection increasingly challenging. A key limitation of current anti-spoofing systems is their limited robustness to unseen synthesis methods. In this work, we transform a self-supervised speech representation model into a Mixture-of-Experts (MoE) architecture to improve generalization. Feed-forward blocks in selected encoder...

    arxiv.org/abs/2606.14639 · PDF

  3. 03

    Moonlight in Latent Space: Chirality and Structural Correspondence Between Beethoven's Op. 27 No. 2 and Machine Learning Mechanisms

    Chen Ying Claude, Zhihan Luo

    cs.SD · cs.AI · eess.AS

    We show that the three movements of Beethoven's "Moonlight Sonata" (Op. 27 No. 2) instantiate three distinct machine learning architectures -- not by analogy, but by structural correspondence. Through computational analysis of the score (entropy, Jensen-Shannon divergence, dissonance, hand distributional overlap, self-similarity matrices, temporal memory decay, and contextual pitch embeddings), we establish four counterintuitive findings: (1)...

    arxiv.org/abs/2606.14612 · PDF

  4. 04

    AudioDER: A Deduplication-Enhanced Reasoning Dataset for Post-Training Large Audio-Language Models

    Hui Geng, Yi Su, Han Yin, Tianjiao Wan, Qisheng Xu, Jiaxin Chen, Zijian Gao, Hengzhu Liu, Xie Chen, Kele Xu

    cs.SD · cs.AI

    Large Audio-Language Models (LALMs) have shown strong performance on a wide range of audio understanding tasks, yet they still struggle with complex audio reasoning. A practical way to improve such capabilities is post-training, whose effectiveness critically depends on the quality and diversity of training data. However, existing audio-language datasets often contain substantial redundancy, where many samples are highly similar in acoustic...

    arxiv.org/abs/2606.14591 · PDF

  5. 05

    The Perceived Fragility of Explanations in Audio Models: Manipulation of Attribution with Unchanged Predictions

    Piotr Kitłowski, Dominik Wiącek, Mateusz Modrzejewski

    cs.SD · cs.AI · cs.LG

    This paper investigates the fragility of post-hoc explanation methods in audio deepfake detection. While previous work on explanation manipulation focused on images using standard $L_p$ metrics, we introduce a psychoacoustic framework that optimizes inaudible perturbations to decouple model attributions from final classifications. We evaluate this vulnerability across state-of-the-art architectures under strict prediction-preserving...

    arxiv.org/abs/2606.14466 · PDF

  6. 06

    Spatio-Temporal Audio Language Modeling for Dynamic Sound Sources

    Oh Hyun-Bin, Kazuki Shimada, Yuhta Takida, Kim Sung-Bin, Toshimitsu Uesaka, Takashi Shibuya, Kyeongyoon Lee,...

    cs.SD · cs.AI · cs.CL

    Sound events are entities with semantic identities, locations, and trajectories, but current audio-language models usually reason about clips as global event content. Conversely, sound event localization models track source directions over time but offer limited semantic coverage for language reasoning. To address this gap, we introduce ST-AudioQA, a spatio-temporal audio QA dataset and benchmark built from first-order ambisonic (FOA)...

    arxiv.org/abs/2606.14141 · PDF

  7. 07

    Mask, Sample, Revise: A Revisable CTMC Inference Stack for Guided Discrete Flow Matching Text-to-Speech

    Alef Iury Siqueira Ferreira, Lucas Rafael Stefanel Gris, Luiz Fernando de Araújo Vidal, Frederico Santos de...

    cs.SD · cs.AI

    Recent alignment-free non-autoregressive (NAR) text-to-speech (TTS) models formulate synthesis as a conditional infilling task, bypassing explicit duration predictors and external aligners. When speech is represented with neural codec tokens, the infilling problem becomes discrete, making Discrete Flow Matching (DFM), a Continuous-Time Markov Chain (CTMC) framework for discrete generation, a natural fit. However, inference-time control for...

    arxiv.org/abs/2606.13989 · PDF

This edition is part of The Daily Abstract — cs.SD archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.