End-to-End Optimized Multi-Stage Vector Quantization of Spectral Envelopes for Speech and Audio Coding.
Mohammad Hassan ValiTom BäckströmPublished in: Interspeech (2021)
Keyphrases
- end to end
- multistage
- vector quantization
- speaker recognition
- codebook design
- distortion measure
- scalar quantization
- speaker identification
- image compression
- reduced complexity
- rate allocation
- vector quantizer
- finite state vector quantization
- speech recognition
- coding scheme
- dynamic programming
- transform coding
- speech signal
- congestion control
- bit allocation
- multipath
- scalable video
- coding method
- multiple description
- inter frame
- optimal policy
- video sequences
- video signals
- multiple description coding
- subband