An Empirical Study on End-to-End Singing Voice Synthesis with Encoder-Decoder Architectures.
Dengfeng KeYuxing LuXudong LiuYanyan XuJing SunChenghao CaiPublished in: CoRR (2021)
Keyphrases
- end to end
- rate allocation
- decoding process
- video codec
- distributed video coding
- error control
- low complexity
- source coding
- noisy channel
- wyner ziv
- turbo codes
- rate distortion
- scalable video
- video coding
- motion compensated prediction
- multipath
- error correction
- motion estimation
- end to end distortion
- rate distortion optimized
- temporal correlation
- error resilience
- admission control
- congestion control
- text localization and recognition
- packet losses
- video compression
- application layer
- transform domain
- compression efficiency
- channel coding
- motion compensated
- inter frame
- bitstream
- video transmission
- forward error correction
- motion compensation
- bit plane
- compressed video
- error concealment
- rate control