Polyphone disambiguation and accent prediction using pre-trained language models in Japanese TTS front-end poster

Citation Author(s):: Rem Hida, Masaki Hamada, Chie Kamada, Emiru Tsunoo, Toshiyuki Sekiya, Toshiyuki Kumakura
Submitted by:: Rem Hida
Last updated:: 6 May 2022 - 2:47am
Document Type:: Poster
Document Year:: 2022
Event:: ICASSP 2022
Presenters:: Rem Hida

Categories:: Speech Synthesis and Generation, including TTS (SPE-SYNT)

Log in to post comments

ICASSP2022_SPE-39.4_poster.pdf

ICASSP2022_SPE-39.4_poster.pdf (168)

Thumbs Up

CITE

QUESTIONS?