作者位次 #5/6ACL 2026Findings· Findings of ACL
R e S tyle- TTS : Relative and Continuous Style Control for Zero-Shot Speech Synthesis
Haitao Li · Chunxiang Jin · Chenglin Li · Wenhao Guan · Zhengxing Huang · Xie Chen
摘要
Zero-shot text-to-speech models can clone a speaker’s timbre from a short reference audio, but they also strongly inherit the speaking style present in the reference. As a result, synthesizing speech with a desired style often requires carefully selecting reference audio, which is impractical whe...