CycleGAN-based speech enhancement for the unpaired training data.

Jing Yuan Changchun Bao

Published in: APSIPA (2019)

Keyphrases

speech enhancement
training data
noisy environments
noise reduction
signal to noise ratio
single channel
speech signal
linear prediction
prior knowledge
smoothing algorithm
vocal tract
wiener filter
edge detection
hidden markov models
speech recognition
text to speech