PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping.

Junhyeok Lee Seungu Han Hyunjae Cho Wonbin Jung

Published in: CoRR (2022)

Keyphrases

speech synthesis
speech recognition
text to speech
vocal tract
prosodic features
speech corpus
pattern recognition
neural network
social networks
data sets
computer vision
objective function
hidden markov models
loss function
mapping function