cs.SD · 2026-07-02 · No. 41

Sound, 2026-07-02.

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

    A Geometric Perspective on Composable Emotion Steering in Text-to-Speech Models

    Siyi Wang, James Bailey, Ting Dang

    cs.SD · cs.LG

    While prior work has explored emotion control in hybrid text-to-speech systems, the geometric properties of these modules, and their implications for steerability, remain poorly understood. We present the first comparative study of speech language model (SLM) and conditional flow-matching (CFM) modules as activation steering sites for mixed emotion speech synthesis. We first characterize emotion representations using linear probing and local...

    arxiv.org/abs/2607.00946 · PDF

  2. 02

    Evaluating Pretrained Music Embeddings for Cross-Performance Jazz Standard Recognition

    Çağrı Eser

    cs.SD · cs.LG

    Recognizing jazz standards from audio is a challenging form of tune-level music retrieval: different performances of the same standard may vary in tempo, key, arrangement, instrumentation, improvisational content, and even whether the head melody is present. We study this problem using a curated subset of the Jazz Trio Database designed for cross-performance standard recognition. We compare a from-scratch trained Harmonic CNN baseline against...

    arxiv.org/abs/2607.00777 · PDF

  3. 03

    Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis

    Zuda Yu, Qianhui Xu, Ting Chen, Junhui Zhang, Tao Fu, Hongjiang Yu, Qiangqing Wang, Yang Song

    cs.SD · cs.AI

    Flow Matching (FM) has emerged as a powerful paradigm for speech generation but remains constrained by high inference latency and timbre leakage. To address these bottlenecks, we propose a unified guidance framework that enhances generation efficiency and robustness through two complementary strategies. On the data front, we introduce Data-guidance via heterogeneous augmentation, encouraging the model to disentangle linguistic content from...

    arxiv.org/abs/2607.00363 · 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.