Very low bit rate speech coding based on HMMs.
Jun HiroiKeiichi TokudaTakashi MasukoTakao KobayashiTadashi KitamuraPublished in: Systems and Computers in Japan (2001)
Keyphrases
- speech recognition
- hidden markov models
- multi stream
- linear prediction
- speech signal
- coding scheme
- automatic speech recognition
- video coding
- phoneme recognition
- video coder
- speech synthesis
- linear predictive
- coding method
- audio visual
- speech recognizer
- bit rate
- video compression
- image sequences
- recognition engine
- speaker dependent
- text to speech
- speaker identification
- broadcast news
- linear predictive coding
- pattern recognition
- chinese named entity recognition
- speaker recognition
- bit allocation
- motion compensated
- motion compensation