GMM-based synchronization rules for HMM-based audio-visual laughter synthesis.
Hüseyin ÇakmakKevin El HaddadThierry DutoitPublished in: ACII (2015)
Keyphrases
- audio visual
- multi stream
- multi modal
- visual information
- gaussian mixture model
- hidden markov models
- visual data
- audio visual speech recognition
- temporal context
- person authentication
- emotion recognition
- multimedia
- audio features
- speaker verification
- human motion
- speaker identification
- sound source
- search engine
- speech recognition
- low level
- domain knowledge
- multiscale
- high level
- web pages