English

In This Environment, As That Speaker: A Text-Driven Framework for Multi-Attribute Speech Conversion

Sound 2025-06-16 v2 Audio and Speech Processing

Abstract

We propose TES-VC (Text-driven Environment and Speaker controllable Voice Conversion), a text-driven voice conversion framework with independent control of speaker timbre and environmental acoustics. TES-VC processes simultaneous text inputs for target voice and environment, accurately generating speech matching described timbre/environment while preserving source content. Trained on synthetic data with decoupled vocal/environment features via latent diffusion modeling, our method eliminates interference between attributes. The Retrieval-Based Timbre Control (RBTC) module enables precise manipulation using abstract descriptions without paired data. Experiments confirm TES-VC effectively generates contextually appropriate speech in both timbre and environment with high content retention and superior controllability which demonstrates its potential for widespread applications.

Keywords

Cite

@article{arxiv.2506.07036,
  title  = {In This Environment, As That Speaker: A Text-Driven Framework for Multi-Attribute Speech Conversion},
  author = {Jiawei Jin and Zhihan Yang and Yixuan Zhou and Zhiyong Wu},
  journal= {arXiv preprint arXiv:2506.07036},
  year   = {2025}
}

Comments

Accepted by Interspeech2025

R2 v1 2026-07-01T03:05:25.578Z