Expressive Speech Synthesis via Modeling Expressions with Variational Autoencoder.

Kei Akuzawa Yusuke Iwasawa Yutaka Matsuo

Published in: INTERSPEECH (2018)

Keyphrases

speech synthesis
speech recognition
text to speech
restricted boltzmann machine
vocal tract
multiscale
natural language
real time
neural network
bayesian networks
data mining
feature selection
image segmentation
optical flow
modeling language
prosodic features