Phoneme-Level Bert for Enhanced Prosody of Text-To-Speech with Grapheme Predictions.

Yinghao Aaron Li Cong Han Xilin Jiang Nima Mesgarani

Published in: ICASSP (2023)

Keyphrases

text to speech
speech synthesis
prosodic features
speech recognition
programming tool
text to speech synthesis
levels of abstraction
english text
word processing
data sets
neural network
case study
pattern recognition
context dependent
visual speech