Discriminative training of HMM stream exponents for audio-visual speech recognition

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 6, Issue , 1998, Pages 3733-3736

  Potamianos, Gerasimos ^a   Graf, Hans Peter ^b  

^a AT AND T LABS RESEARCH   (United States)

^b AT AND T LABS RESEARCH   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; HIDDEN MARKOV MODELS; SIGNAL PROCESSING;

AUDIO VISUAL SPEECH RECOGNITION; AUDIO-VISUAL; DISCRIMINATIVE TRAINING; GENERALIZED PROBABILISTIC DESCENTS; LOG LIKELIHOOD; MULTI-STREAM HMM; TWO-STREAM; VISUAL FEATURE;

SPEECH RECOGNITION;

EID: 0031624666     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.1998.679695     Document Type: Conference Paper

References (10)

1. A. Adjoudani and C. Benoit, "On the integration of auditory and visual parameters in an HMM-based ASR," in Speechreading by Humans and Machines, D.G. Stork and M.E. Hennecke eds., Springer, Berlin, pp. 461-471, 1996.
2. A. Rogozan, P. Deleglise, and M. Alissali, "Adaptive determination of audio and visual weights for automatic speech recognition," Proc. Europ. Tut. Work. Audio-Visual Speech Process. (AVSP), Rhodes, pp. 61-64, 1997.
3. P. Jourlin, "Word dependent acoustic-labial weights in HMM-based speech recognition," Proc. AVSP, Rhodes, pp. 69-72, 1997.
4. G. Potamianos, E. Cosatto, H.P. Graf, and D.B. Roe, "Speaker independent audio-visual database for bimodal ASR," Proc. AVSP, Rhodes, pp. 65-68, 1997.
5. L. Rabiner and B.-H. Juang, Fundamentals of Speech Recognition. Prentice Hall, Englewood Cliffs, 1993.
6. Y.-Lu Chow, "Maximum mutual information estimation of HMM parameters for continuous speech recognition using the TV-best algorithm," Proc. ICASSP, Albuquerque, Vol. 1, pp. 701-704, 1990.
7. J. Hernando, J. Ayarte, and E. Monte, "Optimization of speech parameter weighting for CDHMM word recognition," Proc. Eurospeech, Madrid, Vol. 1, pp. 105-108, 1995.
8. J. Hernando, "Maximum likelihood weighting of dynamic speech features for CDHMM speech recognition," Proc. ICASSP, Munich, Vol. 2, pp. 1267-1270, 1997.
9. CM. del Alamo, F.J. Caminero-Gil, C. de la Torre-Munilla, and L. Hernandez-Gomez, "Codebook weights adaptation for discriminative training of SCHMM-based speech recognition systems," Proc. Eurospeech, Madrid, Vol. 1, pp. 9396, 1995.
10. W. Chou, B.-H. Juang, C.-H. Lee, and F.K. Soong, "A minimum error rate pattern recognition approach to speech recognition," J. Pattern Recog. Art. Intell., Vol. VIII, pp. 5-31, 1994.