Speaker independent audio-visual speech recognition

IEEE International Conference on Multi-Media and Expo

Volumn , Issue II/TUESDAY, 2000, Pages 1073-1076

  Zhang, Y ^a   Levinson, S ^a   Huang, T ^a  

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

Author keywords

[No Author keywords available]

Indexed keywords

MATHEMATICAL MODELS; SIGNAL TO NOISE RATIO; SPURIOUS SIGNAL NOISE; STATISTICAL METHODS;

WORD RECOGNITION ACCURACY (WRA);

SPEECH RECOGNITION;

EID: 0034502214     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (7)

1. Continuous speech recognition by statistical methods
2. The segmental k-means algorithm for estimating parameters of hidden markov models
3. Speaker independent connected word recognition using a syntax-directed dynamic programming procedure
4. Discriminative training of hmm stream exponents for audio-visual speech recognition
5. Fundamentals of speech recognition