Prosodic feature normalization for emotion recognition by using synthesized speech.
Motoyuki SuzukiShohei NakagawaKenji KitaPublished in: KES (2012)
Keyphrases
- synthesized speech
- emotion recognition
- emotional speech
- audio visual
- human computer interaction
- facial expressions
- information fusion
- feature vectors
- sentiment analysis
- speaker verification
- facial images
- physiological signals
- multi modal
- artificial intelligence
- emotional state
- speech recognition
- knn
- emotion classification
- video sequences
- computer vision