WinkTalk: a demonstration of a multimodal speech synthesis platform linking facial expressions to expressive synthetic voices.
Éva SzékelyZeeshan AhmedJoão P. CabralJulie Carson-BerndsenPublished in: SLPAT@HLT-NAACL (2012)
Keyphrases
- facial expressions
- speech synthesis
- speech recognition
- facial expression recognition
- text to speech
- human faces
- face recognition
- face images
- cohn kanade database
- facial expression analysis
- video sequences
- expression recognition
- facial features
- facial actions
- facial images
- emotion recognition
- cohn kanade
- person independent
- real time
- recognition of facial expressions
- head motion
- audio visual
- facial feature points
- feature extraction