TSTNN: Two-Stage Transformer Based Neural Network for Speech Enhancement in the Time Domain.

Kai Wang Bengbeng He Wei-Ping Zhu

Published in: ICASSP (2021)

Keyphrases

speech enhancement
neural network
fuzzy logic
noisy environments
fault diagnosis
noise reduction
signal to noise ratio
single channel
frequency domain
pattern recognition
speech signal
wiener filter
smoothing algorithm
linear prediction
prior knowledge
vocal tract
edge detection
feature extraction
image segmentation