Roles of the average voice in speaker-adaptive HMM-based speech synthesis.

Junichi Yamagishi Oliver Watts Simon King Bela Usabaev

Published in: INTERSPEECH (2010)

Keyphrases

speech synthesis
prosodic features
speech recognition
text to speech
hidden markov models
vocal tract
automatic speech recognition
noisy environments
standard deviation
speech signal
speech sounds
speaker verification
language model
access control
genetic algorithm
speech corpus
real time