Video Realistic Mouth Animation Based on an Audio Visual DBN Model with Articulatory Features and Constrained Asynchrony.
Dongmei JiangPeizhen LiuIlse RavyseHichem SahliWerner VerhelstPublished in: ICIG (2009)
Keyphrases
- multi stream
- audio visual
- high level
- video sequences
- feature vectors
- audio visual speech recognition
- feature extraction
- key frames
- low level
- hidden markov models
- person authentication
- temporal context
- visual information
- multi modal
- multimedia
- spatio temporal
- high dimensional
- training set
- feature space
- three dimensional