Rep2wav: Noise Robust text-to-speech Using self-supervised representations.

Qiushi Zhu Yu Gu Chao Weng Yuchen Hu Lirong Dai Jie Zhang

Published in: CoRR (2023)

Keyphrases

text to speech
image noise
noisy environments
imaging artifacts
greater robustness
speech synthesis
salt pepper
prosodic features
noise model
signal to noise ratio
missing data
median filter
estimation error
registration errors
general purpose
pattern recognition
multiscale
neural network