Binary coding of speech spectrograms using a deep auto-encoder.
Li DengMichael L. SeltzerDong YuAlex AceroAbdel-rahman MohamedGeoffrey E. HintonPublished in: INTERSPEECH (2010)
Keyphrases
- error control
- speech signal
- gray code
- decoding process
- bit rate
- linear prediction
- distributed video coding
- speech recognition
- error correcting
- coding method
- wyner ziv video coding
- efficient compression
- coding efficiency
- predictive coding
- logical operations
- low complexity
- coding scheme
- mode selection
- video coder
- video encoding
- video coding
- motion compensated prediction
- turbo codes
- rate distortion
- motion estimation
- video encoder
- video compression
- error correction
- wyner ziv
- motion compensation
- variable bit rate
- bit allocation
- video coding scheme
- video codec
- mpeg avc
- automatic speech recognition
- image quality
- encoding process
- text to speech
- source coding
- error resilience
- bitstream
- inter frame
- video quality
- non binary
- block size
- bit rate reduction
- image sequences
- intra coding
- mode decision
- compression efficiency
- arithmetic coding
- scalable video coding
- rate control
- macroblock
- compression ratio
- image coding
- computational complexity