TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain.
Kai WangBengbeng HeWei-Ping ZhuPublished in: CoRR (2021)
Keyphrases
- speech enhancement
- neural network
- fuzzy logic
- fault diagnosis
- noisy environments
- noise reduction
- signal to noise ratio
- single channel
- speech signal
- frequency domain
- linear prediction
- wiener filter
- pattern recognition
- multi channel
- vocal tract
- background noise
- additive noise
- image compression
- smoothing algorithm
- wavelet domain
- edge preserving
- image processing