Multimodal Fusion of Body Movement Signals for No-audio Speech Detection.
Xinsheng WangJihua ZhuOdette ScharenborgPublished in: MediaEval (2020)
Keyphrases
- multimodal fusion
- audio visual
- multimodal interfaces
- audio signals
- body movements
- acoustic signals
- cepstral features
- multi modal
- signal processing
- human computer interaction
- automatic analysis
- high robustness
- object detection
- visual information
- relevance feedback
- text to speech
- audio features
- multimedia
- visual data
- motion capture
- speech recognition
- gait recognition
- learning mechanism
- multimodal interaction
- computer vision
- information retrieval
- focus of attention
- data mining
- visual attention
- virtual environment
- low level
- active learning
- image processing