Conditional Variational Auto-Encoder for Text-Driven Expressive AudioVisual Speech Synthesis.

Sara Dahmani Vincent Colotte Valérian Girard Slim Ouni

Published in: INTERSPEECH (2019)

Keyphrases

speech synthesis
text to speech
speech recognition
prosodic features
vocal tract
keywords
bit rate
text retrieval
text documents
speech corpus
free text
image segmentation
data driven
text mining
computer vision
information retrieval
visual information
data mining
bayesian networks
error control