Realistic Mouth-Synching for Speech-Driven Talking Face Using Articulatory Modelling.
Lei XieZhi-Qiang LiuPublished in: IEEE Trans. Multim. (2007)
Keyphrases
- speech recognition
- visual speech
- visual speech recognition
- speech signal
- facial animation
- vocal tract
- recognition engine
- lip reading
- speech synthesis
- facial region
- human faces
- acoustic features
- facial expressions
- hidden markov models
- multi stream
- speaker identification
- mouth region
- audio visual
- automatic speech recognition
- noisy environments
- expression recognition
- data driven
- face images
- real life
- language model
- formant frequencies
- facial expression recognition
- speaker recognition
- text to speech
- facial feature points
- face model
- dialogue system
- active appearance models
- facial images
- lighting conditions
- endpoint detection
- facial feature localization