An adaptive integration based on product hmm for audio-visual speech recognition

Proceedings - IEEE International Conference on Multimedia and Expo

Volumn , Issue , 2001, Pages 813-816

  Kumatani, K ^a,b   Nakamura, S ^a   Shikano, K ^b  

^a ADVANCED TELECOMMUNICATIONS RESEARCH INSTITUTE INTERNATIONAL   (Japan)

^b NARA INSTITUTE OF SCIENCE AND TECHNOLOGY   (Japan)

Author keywords

[No Author keywords available]

Indexed keywords

AUDIO SYSTEMS; INTEGRATION;

ADAPTIVE INTEGRATION; AUDIO AND VISUAL INFORMATION; AUDIO VISUAL SPEECH RECOGNITION; AUTOMATIC SPEECH RECOGNITION SYSTEM; EVALUATION EXPERIMENTS; INDIVIDUAL FEATURES; INTEGRATION METHOD; RECOGNITION ACCURACY;

SPEECH RECOGNITION;

EID: 84885664026     PISSN: 19457871     EISSN: 1945788X     Source Type: Conference Proceeding    
DOI: 10.1109/ICME.2001.1237846     Document Type: Conference Paper

References (7)

1. Satoshi Nakamura, Ron Nagai and Kiyohiro Shikano, "Improved bimodal speech recognition using tied-mixture HMMs and 5000 word Audio-Visual Synchronous database", Proc. Eurospeech, Rhodes, pp. 1623-1626, 1997.
2. Satoshi Nakamura, Hidetoshi Ito and Kiyohiro Shikano, "Stream weight optimization of speech and lip image sequence for Audio-Visual speech recognition", Proc. ICSLP2000, vol. 3, pp. 20-23, 2000.
3. Gerasimos Potamianos and Hans Peter Graf, "Discriminative training of HMM stream exponents for Audio-Visual speech recognition" Proc ICASSP-98 vol. 6 pp. 3733-3736 May 1998.
4. M. J. Tomlinson, M. J. Russell and N. M. Brooke, "'Integrating audio and visual information to provide highly robust speech recognition"', Proc ICASSP-96 vol. 2 pp. 821-824 May 1996.
5. Chiyomi Miyajima, Keiichi Tokuda and Tadashi Kitamura, "Audio-Visual speech recognition using MCE-based HMMs and model-dependent stream weights", Proc. ICSLP2000, vol. 2, pp. 1023-1026, 2000.
6. X. D. Huang, Y. Ariki and N. A. Jack, "HIDDEN MARKOV MODELS FOR SPEECH RECOGNITION", Edinburgh Information Technology Series, EDINBURAGH
7. W. Chou, B.-H. Junang, C.-H. Lee and F. K. Soong, "'A minimum error rate pattern recognition approach to speech recognition"', J. Pattern Recog. Art. Intell., Col. VIII, pp. 5-31, 1994.