An efficient encoder-decoder architecture with top-down attention for speech separation.
Kai LiRunxuan YangXiaolin HuPublished in: CoRR (2022)
Keyphrases
- video codec
- low complexity
- decoding process
- distributed video coding
- error control
- fpga implementation
- video decoder
- speech recognition
- rate distortion
- successive approximation
- noisy channel
- wyner ziv
- motion estimation
- automatic speech recognition
- bitstream
- bit rate
- video sequences
- turbo codes
- video coder
- video compression
- motion compensated prediction
- finite state transducers
- video coding scheme
- motion compensation
- mpeg avc