cs.SD · 2026-08-06 · No. 76
Sound, 2026-08-06.
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-
01
Masked diffusion enables coherent beat tracking
Francesco Foscarin, Filip Korzeniowski, Richard Vogl
cs.SD · cs.AI
Current neural networks for beat tracking generate invalid outputs, such as consecutive downbeats and erratic tempo changes, even when these are not present in the training data. Heavy post-processing techniques can alleviate these problems, but the original cause of this inconsistent behaviour remains unknown. We hypothesise that it stems from inadequate modelling of multiple plausible output beat grids, resulting in an invalid mixture of...
-
02
AudioScape-TTA: A Structured Soundscape Benchmark for Fine-Grained Text-to-Audio Evaluation
Jinting Wang, Yuguang Yang, Shengyu Li, Yan Rong, Shan Yang, Xiaoda Yang, Li Liu
cs.SD · cs.AI
Text-to-audio (TTA) generation has recently achieved remarkable progress in synthesizing realistic audio from natural language descriptions. However, determining whether generated audio faithfully satisfies complex textual instructions remains challenging. Existing benchmarks mainly rely on global similarity metrics, providing limited insight into fine-grained semantic failures. To address this limitation, we introduce...
-
03
Helping Music Co-Creation Agents 'Listen' Well: Hierarchical Self-Supervised World Models for Understanding and Generation
Scott H. Hawley
cs.SD · cs.LG · eess.AS
Collaborative music agents need internal representations rich enough to support both understanding and generation, yet flexible enough for a workflow where the human retains agency. We present a hierarchical self-supervised ``world model'' for symbolic music: a 2.55M-parameter Swin V2 encoder trained on MIDI piano-roll images with JEPA-style objectives (pitch- and time-shift equivariance, masked embedding prediction, and a distributional...
-
04
HyPASE: Hyperbolic Geometry for Parameter-Efficient Speech Emotion Fine-Tuning Framework for Large Audio-Language Models
Tian Jin, Ruikang Zhang, Zefeng Zhao, Ding Luo, Jin Zeng
cs.SD · cs.AI
Large Audio-Language Models (LALMs) excel at general speech understanding; however, adapting them to fine-grained tasks like Speech Emotion Recognition (SER) remains a significant bottleneck. Current Parameter-Efficient Fine-Tuning (PEFT) methods typically operate in flat Euclidean space, and this geometry fails to capture the multi-granularity nature of emotion cues, which range from low-level prosody to high-level semantics. To address...
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.