Average-Voice-Based Speech Synthesis Using HSMM-Based Speaker Adaptation and Adaptive Training.

Junichi Yamagishi Takao Kobayashi

Published in: IEICE Trans. Inf. Syst. (2007)

Keyphrases

speech synthesis
speech recognition
speaker adaptation
text to speech
vocal tract
prosodic features
speaker independent
speech recognizer
automatic speech recognition
speaker dependent
hidden markov models
language model
pattern recognition
speech signal
noisy environments
training set