SRTNet: Time Domain Speech Enhancement Via Stochastic Refinement.

Zhibin Qiu Mengfan Fu Yinfeng Yu LiLi Yin Fuchun Sun Hao Huang

Published in: CoRR (2022)

Keyphrases

speech enhancement
noise reduction
noisy environments
signal to noise ratio
frequency domain
single channel
speech signal
vocal tract
linear prediction
speech recognition
wiener filter
computer vision
image segmentation
image sequences
background noise
smoothing algorithm