Expressive visual text to speech and expression adaptation using deep neural networks.

Jonathan Parker Ranniery Maia Yannis Stylianou Roberto Cipolla

Published in: ICASSP (2017)

Keyphrases

text to speech
neural network
speech synthesis
pattern recognition
programming tool
prosodic features
low level

text to speech synthesis
self organizing maps
feed forward
english text
visual information
multi layer
word processing

fuzzy systems
visual perception
multimodal interaction
high level
genetic algorithm
neural network model
gene expression

recurrent neural networks
training process
back propagation
visual features
general purpose
artificial neural networks