Perception of prosodic variation for speech synthesis using an unsupervised discrete representation of F0.

Zack Hodari Catherine Lai Simon King

Published in: CoRR (2020)

Keyphrases

speech synthesis
speech recognition
prosodic features
text to speech
vocal tract
supervised learning
translation invariant
continuous domains
representation scheme
visual perception
unsupervised learning
language model
image processing
data sets
hidden markov models
perceptual information
machine learning