A coupled HMM approach to video-realistic speech animation.
Lei XieZhi-Qiang LiuPublished in: Pattern Recognit. (2007)
Keyphrases
- facial animation
- speech recognition
- hidden markov models
- speech signal
- temporal coherence
- multi stream
- video sequences
- video editing
- automatic speech recognition
- automatic speech recognition systems
- video data
- broadcast news
- video frames
- motion capture data
- real time
- content based video retrieval
- audio signals
- multimedia
- video content
- recognition engine
- video retrieval
- phoneme recognition
- digital audio
- video streams
- facial expressions
- special effects
- video clips
- speech synthesis
- computer graphics
- audio video
- real world
- video analysis
- video surveillance
- digital video
- video database
- speech recognizer
- visual speech
- real time rendering
- keyword spotting
- computer vision
- image sequences
- language model
- visual speech recognition
- audio visual
- visual data