Audio-visual speech synchronization detection using a bimodal linear prediction model.
Kshitiz KumarJirí NavrátilEtienne MarcheretVit LibalGanesh N. RamaswamyGerasimos PotamianosPublished in: CVPR Workshops (2009)
Keyphrases
- audio visual
- prediction model
- multi stream
- multi modal
- regression model
- visual information
- audio visual speech recognition
- emotion recognition
- speaker verification
- visual data
- multimedia
- neural network
- hidden markov models
- audio features
- machine learning
- e learning
- feature selection
- search engine
- exponential smoothing