Psychologically-Inspired Audio-Visual Speech Recognition Using Coarse Speech Recognition and Missing Feature Theory.
Kazuhiro NakadaiTomoaki KoiwaPublished in: J. Robotics Mechatronics (2017)
Keyphrases
- speech recognition
- cepstral coefficients
- audio visual speech recognition
- visual speech
- speaker identification
- hidden markov models
- speech signal
- noisy environments
- visual speech recognition
- multi stream
- automatic speech recognition
- speech recognition technology
- audio signal
- audio visual
- language model
- feature set
- speaker recognition
- broadcast news
- speech synthesis
- multiresolution
- pattern recognition
- audio signals
- acoustic features
- speaker verification
- machine learning