Pairing audio speech and various visual displays: binding or not binding?
Aymeric DevergieFrédéric BerthommierNicolas GrimaultPublished in: AVSP (2009)
Keyphrases
- audio stream
- visual information
- audio visual
- gaze contingent
- speaker identification
- low level
- audio signals
- emotion recognition
- cross modal
- visual speech
- content based video retrieval
- text to speech
- high level
- broadcast news
- visual representation
- speech recognition
- visual features
- hidden markov models
- audio features
- audio signal
- speech signal
- visual data
- speech processing
- digital audio
- acoustic signals
- multimedia