cs.SD · 2026-10-24 · No. 152
Sound, 2026-10-24.
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-
01
Muting Tokens: Exploring Token Sparsification for Efficient Audio Transformers
Shreya Sajid, Fabrizio Julian Piva, Hiram Rayo Torres Rodriguez, Elif Ceren Gok Yildirim, Murat Onur Yildirim,...
cs.SD · cs.LG · eess.AS
Transformer-based models have shown strong performance across diverse tasks, but their reliance on self-attention mechanisms often leads to high computational costs. Token sparsification, which reduces the number of tokens processed in transformer layers, offers a promising solution to maintain performance while improving efficiency. However, although widely studied in the vision and language domains, token sparsification remains...
-
02
Predicting Music Valence and Arousal via Textual and Multimodal In-Context Learning in Large Language Models
Chi-En Dai, Chih-Pin Tan, Yi-Hsuan Yang
cs.SD · cs.AI · cs.CL
While arousal can be reliably predicted from musical audio, emotional valence remains difficult to model due to its subjective and context-dependent nature. In this work, we investigate the potential of in-context learning (ICL) with large language models to advance continuous valence and arousal prediction. Rather than predicting emotion scores directly, our framework leverages contextual demonstrations from an auxiliary dataset to refine...
-
03
MQAScore: Fine-Grained Text-Music Alignment Evaluation via Large Audio Language Model
Wei-Jaw Lee, Chun-Ping Wang, Xuanjun Chen, Yi-Hsuan Yang
cs.SD · cs.AI · eess.AS
Text-to-music alignment is commonly evaluated by the global similarity between text and audio embeddings, which collapses all described attributes into a single score and obscures which ones are missing. We instead introduce MQAScore, which verifies each atomic musical concept along five clip-level dimensions (genre, instrument, mood/theme, vocal, and usage) by the probability that a large audio language model (LALM) answers affirmatively to...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.