Improving Emotional Speech Synthesis by Using SUS-Constrained VAE and Text Encoder Aggregation.

Fengyu Yang Jian Luan Yujun Wang

Published in: CoRR (2021)

Keyphrases

speech synthesis
text to speech
speech recognition
prosodic features
vocal tract
text retrieval
information retrieval
rate distortion
bit rate
text mining
free text
hidden markov models
keywords
affect sensing
low complexity
word processing
pattern recognition
database