1 code implementation • 10 May 2020 • Zexin Cai, Chuxiong Zhang, Ming Li
The constraint is taken by an added loss related to the speaker identity, which is centralized to improve the speaker similarity between the synthesized speech and its natural reference audio.
no code implementations • 3 Jul 2019 • Zexin Cai, Yaogen Yang, Chuxiong Zhang, Xiaoyi Qin, Ming Li
This paper describes a conditional neural network architecture for Mandarin Chinese polyphone disambiguation.