Can I read VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech on EtoBox?

VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech by Du, Chenpeng; Guo, Yiwei; Wang, Hankun; Yang, Yifan; Niu, Zhikang; Wang, Shuai; Zhang, Hui; Chen, Xie; Yu, Kai is a scholarly article available to read on EtoBox.

What is VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech about?

Recent TTS models with decoder-only Transformer architecture, such as SPEAR-TTS and VALL-E, achieve impressive naturalness and demonstrate the ability for zero-shot adaptation given a speech prompt. However, such decoder-only TTS models lack monotonic alignment constraints, sometimes leading to hallucination issues such as mispronunciation, word skipping and repeating. To address this limitation, we propose VALL-T, a generative Transducer model that introduces shifting relative position embeddings for input phoneme sequence, explicitly indicating the monotonic generation process while maintaining the architecture of decoder-only Transformer. Consequently, VALL-T retains the capability of prompt-based zero-shot adaptation and demonstrates better robustness against hallucinations with a relative reduction of 28.3% in the word error rate.

Author

Du, Chenpeng; Guo, Yiwei; Wang, Hankun; Yang, Yifan; Niu, Zhikang; Wang, Shuai; Zhang, Hui; Chen, Xie; Yu, Kai

Published

2024

Language

EN