Appearance and shape-based hybrid visual feature extraction: toward audio-visual automatic speech recognition.
Saswati DebnathPinki RoyPublished in: Signal Image Video Process. (2021)
Keyphrases
- audio visual
- automatic speech recognition
- visual information
- feature extraction
- visual data
- speech recognition
- multi modal
- visual features
- speech signal
- hidden markov models
- acoustic features
- multi stream
- audio features
- conversational speech
- image classification
- speaker verification
- broadcast news
- image processing
- emotion recognition
- low level
- principal component analysis
- object recognition
- pattern recognition
- visual content
- multimedia
- eye movements
- semantic information
- video data
- video search
- feature vectors
- feature space
- speaker identification
- high level
- computer vision