Coarse speech recognition by audio-visual integration based on missing feature theory.
Tomoaki KoiwaKazuhiro NakadaiJun-ichi ImuraPublished in: IROS (2007)
Keyphrases
- speech recognition
- audio visual
- audio visual speech recognition
- multi stream
- multi modal
- hidden markov models
- automatic speech recognition
- cepstral coefficients
- visual data
- speech signal
- language model
- speech synthesis
- noisy environments
- visual information
- speech recognizer
- multimedia
- speech recognition systems
- speaker verification
- pattern recognition
- neural network
- emotion recognition
- image features
- feature vectors
- face recognition