cs.SD · 2026-10-02 · No. 131

Sound, 2026-10-02.

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

    LAST: Looped Audio Spectrogram Transformer

    Haider Al-Tahan, Sean O'Brien, Anastasia Razdaibiedina, N. Apurva Ratan Murty

    cs.SD · cs.LG · eess.AS

    Increasing depth of transformer models improves recognition, but it comes at a substantial cost. Each additional layer requires more parameters, which makes the process computationally inefficient. We ask whether additional processing can focus on integrating features already computed. Looped Audio Spectrogram Transformer (LAST) first processes all tokens, then reuses the same blocks to refine only the class token over fixed audio features,...

    arxiv.org/abs/2610.01926 · PDF

  2. 02

    From Isolated Feature to Orbits: Discovering Music Concepts via Multi-SAE Alignment

    Liwei Lin, Gus Xia

    cs.SD · cs.AI

    How can we understand what a music foundation model has learned \textit{internally}? Most interpretability approaches, such as probing and Sparse Autoencoders (SAEs), focus on identifying individual features with minimal structural assumptions. We argue that many concepts are better understood as \textit{structured relations} rather than isolated features. This is especially prominent in music, where tonal structures are organized in the...

    arxiv.org/abs/2610.01864 · PDF

  3. 03

    Beyond Decodability: Do Acoustic Factors Drive Predictions in Speech-Based Alzheimer's Assessment?

    Serli Kopar, Alkis Koudounas, Roshan P. Rane, Sam Gijsen, Paula A. Perez-Toro, Kerstin Ritter

    cs.SD · cs.CL · cs.LG · eess.AS

    Speech-based Alzheimer's disease (AD) assessments increasingly rely on pretrained self-supervised learning (SSL) models that learn acoustic representations directly from raw audio, exposing the model to recording factors. We ask whether such factors are merely encoded in SSL representations or can systematically alter predictions. Using ADReSSo and three large SSL backbones, we apply controlled noise and reverberation interventions to...

    arxiv.org/abs/2610.01846 · 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.