cs.SD · 2026-09-04 · No. 105

Sound, 2026-09-04.

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

01 — The papers

3 entries
  1. 01

    Masked Autoregressive Speech Enhancement with Continuous Neural Audio Codec Representations

    Yoto Fujita, Simon Leglaive, Laurent Girin

    cs.SD · cs.AI

    Most previous work on speech enhancement (SE) based on masked generative modeling relied on discrete token representations of audio signals, obtained using neural audio codecs (NACs). However, a recent study has shown that continuous latent representations of NACs can be advantageous for SE in terms of speech quality and intelligibility. In this work, we propose masked autoregressive SE (MARSE), a method for SE based on iterative decoding of...

    arxiv.org/abs/2609.03940 · PDF

  2. 02

    Test-time adaptation for speech enhancement with an autoregressive speech prior

    Sofiene Kammoun, Simon Leglaive, Xavier Alameda-Pineda, Timo Gerkmann

    cs.SD · cs.AI

    Test-time adaptation (TTA) offers a promising direction for improving speech enhancement models under mismatched acoustic conditions, without requiring access to labeled target data. In this work, we propose a single-utterance TTA method that regularizes a pretrained speech enhancement model using an autoregressive prior trained on clean speech latent representations extracted from a neural audio codec. Adaptation is performed by minimizing...

    arxiv.org/abs/2609.03622 · PDF

  3. 03

    StrixAE: An Intelligent Agent for Audio Enhancement under Complex Distortion Coupling in Real-World Scenarios

    Chenglin Wu, Junjie Wu, Jinhang Chen, Mingyang Chen, Zixu Lin, Jiabian Chen, Xinghao Ding, Xiaotong Tu

    cs.SD · cs.AI

    Audio enhancement in real-world scenarios involves complex distortion couplings and requires personalized enhancement. Existing solutions struggle to address both simultaneously. To improve robustness and enable autonomous operation in such scenarios, we propose StrixAE, an agent based on a multimodal large language model (MLLM). StrixAE leverages the MLLM as a controller to coordinate multiple audio enhancement and personalization models. To...

    arxiv.org/abs/2609.03414 · 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.