Multi-stream spectral representation for statistical parametric speech synthesis.

Kayoko Yanagisawa Ranniery Maia Yannis Stylianou

Published in: ICASSP (2016)

Keyphrases

speech synthesis
multi stream
speech recognition
audio visual speech recognition
text to speech
parametric representation
hidden markov models
neural network
audio visual
vocal tract
data sets
bayesian networks
image data
text classification