A new approach to integrate audio and visual features of speech

IEEE International Conference on Multi-Media and Expo

Volumn , Issue II/TUESDAY, 2000, Pages 1093-1096

  Pan, H ^a   Liang, Z P ^a   Huang, T S ^a  

^a University of Illinois at Urbana Champaign   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

LEARNING ALGORITHMS; MARKOV PROCESSES; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; PROBABILISTIC LOGICS;

SPEECH INTEGRATION;

SPEECH ANALYSIS;

EID: 0034509395     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (8)

1. Computer lipreading for improved accuracy in automatic speech recognition
2. Feature based representation for audio-visual speech recognition
3. Mixed memory markov model: Decomposing complex stochastic processes as mixture of simpler ones
4. Coupled hidden markov models for modeling interacting processes
5. Exploiting the dependencies in information fusion
6. Lipreading from color motion video
7. Information theory and statistical mechanics