EmoShapelets: Capturing local dynamics of audio-visual affective speech.
Yuan ShangguanEmily Mower ProvostPublished in: ACII (2015)
Keyphrases
- audio visual
- emotion recognition
- multi modal
- affective states
- multi stream
- visual information
- visual data
- speaker verification
- multimedia
- audio visual speech recognition
- temporal context
- person authentication
- audio features
- speech recognition
- text classification
- image classification
- pattern recognition
- computer vision