cs.SD · 2026-06-09 · No. 18

Sound, 2026-06-09.

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

    Multi-View Speech Representation Learning for Parkinson's Disease Detection Using Context-guided Cross-modal Attention

    George Theodosiou, Loukas Ilias, Dimitris Askounis

    cs.SD · cs.LG

    Parkinson's disease (PD) is a progressive neurodegenerative disorder that frequently causes speech impairments associated with hypokinetic dysarthria. As speech production relies on the precise coordination of complex neuromuscular mechanisms, speech analysis has emerged as a promising non-invasive and cost-effective biomarker for early PD detection. Recent deep learning approaches have shown encouraging results; however, most existing...

    arxiv.org/abs/2606.09271 · PDF

  2. 02

    Physics-Guided Sequence-Based Generative Framework for Acoustic Metamaterial Inverse Design

    Yijie Li, Jiahao Xu, Ching-Chih Tsao, Lili Qiu, Jingxian Wang

    cs.SD · cs.AI

    Acoustic metamaterial (AMM) inverse design is particularly challenging for broadband target responses due to acoustic dispersion: a structure that matches the desired response at one frequency may deviate at others, and modifying geometry to improve one sub-band often perturbs neighboring sub-bands. Yet existing broadband inverse-design approaches are either constrained by predefined templates, or rely on image representations that fail to...

    arxiv.org/abs/2606.09266 · PDF

  3. 03

    End-to-End Training for Discrete Token LLM based TTS System

    Changfeng Gao, Yong Ren, Jun Yuan, Ye Bai, Zhao You, ShiDong Shang

    cs.SD · cs.AI

    Recent state-of-the-art (SOTA) text-to-speech (TTS) systems typically adopt a cascaded pipeline consisting of a speech tokenizer, an autoregressive large language model (LLM), and a diffusion based flow-matching (FM) model, with these components trained independently. In this paper, we propose a fully end-to-end (E2E) optimization framework that unifies the training of the speech tokenizer, LLM, FM model, and an additional reward model (RM)....

    arxiv.org/abs/2606.09234 · 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.