Deep Encoder-Decoder Models for Unsupervised Learning of Controllable Speech Synthesis.

Gustav Eje Henter Xin Wang Junichi Yamagishi

Published in: CoRR (2018)

Keyphrases

unsupervised learning
speech synthesis
low complexity
probabilistic model
deep architectures
model selection
deep learning
language model
video codec
data mining
pattern recognition
active learning
motion estimation
semi supervised
supervised learning