Joint Adversarial Training of Speech Recognition and Synthesis Models for Many-to-One Voice Conversion Using Phonetic Posteriorgrams

Yuki SAITO  Kei AKUZAWA  Kentaro TACHIBANA  

Publication:   IEICE TRANSACTIONS on Information and Systems
Publicized: 2020/06/12
DOI: 10.1587/transinf.2019EDP7297
Full Text: PDF(401.5KB)