A Novel Lip Descriptor for Audio-Visual Keyword Spotting Based on Adaptive Decision Fusion.
Pingping WuHong LiuXiaofei LiTing FanXuewu ZhangPublished in: IEEE Trans. Multim. (2016)
Keyphrases
- audio visual
- decision fusion
- keyword spotting
- audio visual speech recognition
- multi modal
- speech recognition
- visual information
- multi stream
- visual data
- multimedia
- hidden markov models
- image retrieval
- neural network
- action recognition
- fusion method
- data fusion
- contextual information
- data management
- feature extraction
- face recognition
- data mining