|国家预印本平台
首页|StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion

StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion

StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion

来源:Arxiv_logoArxiv
英文摘要

Voice Conversion (VC) modifies speech to match a target speaker while preserving linguistic content. Traditional methods usually extract speaker information directly from speech while neglecting the explicit utilization of linguistic content. Since VC fundamentally involves disentangling speaker identity from linguistic content, leveraging structured semantic features could enhance conversion performance. However, previous attempts to incorporate semantic features into VC have shown limited effectiveness, motivating the integration of explicit text modeling. We propose StarVC, a unified autoregressive VC framework that first predicts text tokens before synthesizing acoustic features. The experiments demonstrate that StarVC outperforms conventional VC methods in preserving both linguistic content (i.e., WER and CER) and speaker characteristics (i.e., SECS and MOS). Audio demo can be found at: https://thuhcsi.github.io/StarVC/.

Fengjin Li、Jie Wang、Yadong Niu、Yongqing Wang、Meng Meng、Jian Luan、Zhiyong Wu

通信

Fengjin Li,Jie Wang,Yadong Niu,Yongqing Wang,Meng Meng,Jian Luan,Zhiyong Wu.StarVC: A Unified Auto-Regressive Framework for Joint Text and Speech Generation in Voice Conversion[EB/OL].(2025-06-03)[2025-07-16].https://arxiv.org/abs/2506.02414.点此复制

评论