Multi-Scale Temporal Frequency Convolutional Network With Axial Attention for Speech Enhancement.
Guochang ZhangLibiao YuChunliang WangJianqiang WeiPublished in: ICASSP (2022)
Keyphrases
- multiscale
- speech enhancement
- convolutional network
- coarse to fine
- noise reduction
- noisy environments
- convolutional neural networks
- signal to noise ratio
- scale space
- edge detection
- single channel
- image processing
- focus of attention
- natural images
- linear prediction
- vocal tract
- wavelet decomposition
- speech signal
- computer vision
- image segmentation
- prior knowledge