Audio-visual speech recognition using lip movement extracted from side-face images.
Tomoaki YoshinagaSatoshi TamuraKoji IwanoSadaoki FuruiPublished in: AVSP (2003)
Keyphrases
- audio visual
- face images
- facial features
- face recognition
- audio visual speech recognition
- multi modal
- facial expressions
- multi stream
- human faces
- emotion recognition
- principal component analysis
- high resolution
- input image
- visual information
- face databases
- feature extraction
- multimedia
- feature points
- training set
- visual data
- face verification
- audio features
- feature vectors
- face detection
- human computer interaction
- facial images
- image set
- data sets
- three dimensional
- computer vision