一作ACL 2026Findings· Findings of ACL
V oice S tar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolation
Puyuan Peng · Zhisheng Zheng · Shang-Wen Li · Abdelrahman Mohamed · David Harwath
摘要
We present VoiceStar, the first zero-shot TTS model that achieves both output duration control and extrapolation. VoiceStar is an autoregressive encoder-decoder neural codec language model, that leverages a novel Progress-Monitoring Rotary Position Embedding (PM-RoPE) and is trained with Continua...