Convolutional Recurrent Neural Network Based on Short-Time Discrete Cosine Transform for Monaural Speech Enhancement.
Jinzuo GuoYi ZhouHongqing LiuYongbao MaPublished in: ChinaCom (2022)
Keyphrases
- discrete cosine transform
- speech enhancement
- noise reduction
- noisy environments
- signal to noise ratio
- single channel
- image compression
- speech signal
- transform domain
- dct coefficients
- neural network
- linear prediction
- filter bank
- vocal tract
- wiener filter
- background noise
- additive noise
- multi channel
- edge detection
- multiscale
- image processing
- subband
- image restoration
- automatic speech recognition