no code implementations • 5 Jun 2023 • Dengfeng Ke, Yayue Deng, Yukang Jia, Jinlong Xue, Qi Luo, Ya Li, Jianqing Sun, Jiaen Liang, Binghuai Lin
Regressive Text-to-Speech (TTS) system utilizes attention mechanism to generate alignment between text and acoustic feature sequence.
no code implementations • 3 May 2023 • Jinlong Xue, Yayue Deng, Fengping Wang, Ya Li, Yingming Gao, JianHua Tao, Jianqing Sun, Jiaen Liang
However, it is still a challenge to comprehensively model the conversation, and a majority of conversational TTS systems only focus on extracting global information and omit local prosody features, which contain important fine-grained information like keywords and emphasis.
1 code implementation • 20 Mar 2022 • Jinlong Xue, Yayue Deng, Yichen Han, Ya Li, Jianqing Sun, Jiaen Liang
In recent years, neural network based methods for multi-speaker text-to-speech synthesis (TTS) have made significant progress.