Statistical model training technique for speech synthesis based on speaker class.

Yusuke Ijima Noboru Miyazaki Hideyuki Mizuno

Published in: SSW (2013)

Keyphrases

statistical model
speech synthesis
speech recognition
prosodic features
statistical models
vocal tract
text to speech
statistical distribution
training set
hidden markov models
automatic speech recognition
computer vision
language model
set of training images