Evaluating Speech, Face, Emotion and Body Movement Time-series Features for Automated Multimodal Presentation Scoring.
Vikram RamanarayananChee Wee LeongLei ChenGary FengDavid Suendermann-OeftPublished in: ICMI (2015)
Keyphrases
- multimodal fusion
- audio visual
- facial expressions
- emotional speech
- emotion recognition
- emotional state
- low level
- multi modal
- feature vectors
- body movements
- multimodal interfaces
- visual speech
- high dimensional
- feature space
- software engineering
- speech recognition
- temporal information
- lexical features
- recognition engine