cs.SD · 2026-08-11 · No. 81

Sound, 2026-08-11.

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

01 — The papers

4 entries
  1. 01

    Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions

    Oluwanifemi Bamgbose, Simon Rosen, Jash Shah, Lindsay Devon Brin, Hoang H Nguyen, Anke Koelzer, Rachel Hansen, Tara...

    cs.SD · cs.AI · cs.CL

    Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Models (Audio-LLM) judges) are expected to reflect human perception, yet it is unclear how well they capture the distinct aspects of speech that listeners actually perceive. We deconstruct "naturalness" into a linguistically grounded annotation schema spanning 10 distinct perceptual dimensions, and use it to construct the first...

    arxiv.org/abs/2608.09930 · PDF

  2. 02

    MADBench: A Benchmark for Modality-Aware Audio Deepfake Detection

    Yanqiu Li, Yang Xiao, Jisheng Bai, Bin Chen, Hong Jia, Ting Dang

    cs.SD · cs.AI

    Recent advances in speech synthesis and audio generation have made high-fidelity acoustic forgery low-cost and difficult to attribute, enabling a realistic attack scenario in which speech and background audio are independently manipulated over otherwise authentic video. Yet existing research either focuses on visual manipulation, addresses speech detection in isolation, or conflates speech and non-speech audio as a single undifferentiated...

    arxiv.org/abs/2608.09593 · PDF

  3. 03

    RAG-Audio: Retrieval-Augmented Generation for Faithful Brain-to-Audio Reconstruction

    Ambuj Mehrish, Sebastiano Vascon

    cs.SD · cs.AI

    Brain-to-audio reconstruction is limited by \emph{prior domination}: when a pretrained generator is conditioned on a weak neural signal, it produces realistic but stimulus-inaccurate audio. We introduce RAG-Audio, which decodes fMRI into a semantic audio embedding, retrieves a matching real-audio exemplar, and initializes the frozen generator's sampling trajectory from that exemplar while retaining the decoded embedding as conditioning. On...

    arxiv.org/abs/2608.09331 · PDF

  4. 04

    DAVE: A Decoupled Audio-Visual Enhancement Framework for Real-World Speech Separation

    Wei Zhou, Wanyi Ning, Yinshang Guo, Qianxiao Fang, Haitao Qian, Yingpeng Li

    cs.SD · cs.AI

    Audio-visual speech enhancement under real-world conditions remains challenging due to unreliable visual inputs and the lack of large-scale training data with realistic acoustic conditions. Existing approaches usually fuse visual features directly into the separation network, making them vulnerable to degraded visual signals. In this paper, we present DAVE, a decoupled audio-visual enhancement framework for real-world speech separation....

    arxiv.org/abs/2608.09288 · 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.