An efficient encoder-decoder architecture with top-down attention for speech separation.
Kai LiRunxuan YangXiaolin HuPublished in: ICLR (2023)
Keyphrases
- video codec
- low complexity
- decoding process
- distributed video coding
- error control
- wyner ziv video coding
- successive approximation
- mpeg avc
- noisy channel
- speech recognition
- rate distortion
- video coding
- fpga implementation
- image coding
- bit rate
- video coding scheme
- transform domain
- hardware implementation
- error concealment
- finite state transducers
- wyner ziv
- motion compensated
- temporal correlation
- audio visual
- distributed source coding
- video decoder