Face reading from speech - predicting facial action units from audio cues.
Fabien RingevalErik MarchiMarc MehuKlaus R. SchererBjörn W. SchullerPublished in: INTERSPEECH (2015)
Keyphrases
- facial action units
- multimodal fusion
- audio visual
- prosodic features
- audio stream
- multimodal interfaces
- facial expressions
- text to speech
- facial expression recognition
- broadcast news
- visual speech
- facial actions
- speaker identification
- human faces
- speech recognition
- facial animation
- facial images
- multimedia
- semantic relationships
- human computer interaction
- face verification
- principal component analysis
- semantic relations
- visual information
- user interface
- high level
- face images