Time-Domain Speech Enhancement Assisted by Multi-Resolution Frequency Encoder and Decoder.
Hao ShiMasato MimuraLongbiao WangJianwu DangTatsuya KawaharaPublished in: ICASSP (2023)
Keyphrases
- speech enhancement
- multiresolution
- video codec
- decoding process
- distributed video coding
- low complexity
- error control
- single channel
- noisy channel
- noise reduction
- noisy environments
- signal to noise ratio
- frequency domain
- rate distortion
- speech signal
- wyner ziv
- wavelet decomposition
- linear prediction
- motion estimation
- wavelet transform
- wiener filter
- multi channel
- video coding
- quadtree
- background noise
- subband
- smoothing algorithm
- bit rate
- wavelet domain
- filter bank
- vocal tract
- motion compensation
- independent component analysis
- wavelet coefficients
- speech recognition