Timing and interaction of visual cues for prominence in audiovisual speech perception.
David HouseJonas BeskowBjörn GranströmPublished in: INTERSPEECH (2001)
Keyphrases
- visual cues
- visual information
- audio visual
- depth cues
- low level
- emotional state
- emotion recognition
- mid level
- visual data
- human computer interaction
- visual features
- speech recognition
- multimodal interfaces
- speech signal
- multiple visual cues
- databases
- multi modal
- high level
- automatic speech recognition
- multimodal interaction
- human communication
- video retrieval
- key frames
- video sequences
- face recognition
- three dimensional
- machine learning