cs.SD · 2026-10-08 · No. 137
Sound, 2026-10-08.
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
Steerspeech: Activation Steering For Emotion Control In Generated Speech
Afsara Benazir, Darius Pétermann, Felix Xiaozhu Lin, Salar Rahili
cs.SD · cs.LG · eess.AS
Pretrained text-to-speech (TTS) models can generate expressive speech, but reliable inference-time emotion control remains challenging: prompts and reference audio offer coarse, inconsistent control, whereas specialized conditioning and model adaptation require costly training. We present SteerSpeech, a lightweight activation-steering framework that controls emotion by injecting steering vectors into hidden activations. For each target...
-
02
MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User Intent
Zekai Liu, Zhilin Wang, Xuzheng He, Yu Cheng, Yang Yang
cs.SD · cs.AI
Text-to-music systems produce increasingly convincing audio, yet evaluation reveals little about whether the result matches user intent. A global text-audio relevance score can overlook the implicit intent in underspecified prompts and mask failures in specific requirements, such as instrumentation, structure, rhythm, or mood progression. To bridge this gap, we formulate text-to-music intent alignment as satisfying a per-request rubric of...
-
03
CARES: A Controlled Synthetic Benchmark of Speaker Reactions to Sound
Marcel Gibier, Thomas Thebaud, Olivier Boëffard, Jean-François Bonastre
cs.SD · cs.LG
Automatic audio scene description turns a recording into a text account of a situation. One difficulty is deciding which elements of the audio should be kept, since a description cannot include them all. Annotators disagree about this, making a ground truth hard to obtain. In this work, we first define the ground truth, then generate the data. We focus on audio events and define sound salience with a simple rule: a sound is salient when a...
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.