An improved minimum generation error based model adaptation for HMM-based speech synthesis.

Yi-Jian Wu Long Qin Keiichi Tokuda

Published in: INTERSPEECH (2009)

Keyphrases

speech synthesis
speech recognition
hidden markov models
text to speech
prosodic features
error rate
vocal tract
generation process
speech corpus
recognition rate
generation method
language model
error free
evolutionary algorithm
video sequences
feature selection
square error
data sets