Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions.

Yinghao Aaron Li Cong Han Xilin Jiang Nima Mesgarani

Published in: CoRR (2023)

Keyphrases

text to speech
speech synthesis
prosodic features
text to speech synthesis
programming tool
speech recognition
word processing
higher level
levels of abstraction
hidden markov models
pattern recognition
context dependent