Approaches to visual speech processing based on the MPEG-4 face animation standard

IEEE International Conference on Multi-Media and Expo

Volumn , Issue I/MONDAY, 2000, Pages 575-578

  Petajan, E ^a  

^a Face2face animation inc   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ANIMATION; COMPUTATIONAL METHODS; DATA ACQUISITION; DATABASE SYSTEMS; GESTURE RECOGNITION; MOTION PICTURES; SPEECH RECOGNITION; VIDEO SIGNAL PROCESSING;

MOTION PICTURE EXPERTS GROUP (MPEG);

SPEECH PROCESSING;

EID: 0034502124     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (18)

1. Automatic lipreading to enhance speech recognition
2. A hybrid approach to bimodal speech recognition
3. Medium vocabulary audiovisual speech recognition
4. Audio-visual speech recognition compared across two architectures
5. Active shape models for visual speech feature extraction
6. Continuous optical automatic speech recognition
7. Automatic computer lip-reading using fuzzy set theory
8. A diffusion network approach to visual speech recognition
9. Multi-modal system for locating heads and faces
10. Sensory integration and speechreading by humans and machines
11. Feature based representation for audio-visual speech recognition
12. Audio-visual sensorfusion with neural architectures
13. On the use of visual information for improving audio-based speaker recognition
14. A tool for designing MPEG-4 compliant expressions and animations on VRML cartoon faces
15. User interactive MPEG-4 compatible facial animation system