Automatic speech recognition based on Weighted Minimum Classification Error (W-MCE) training method

2007 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2007, Proceedings

Volumn , Issue , 2007, Pages 278-283

  Fu, Qiang ^a   Juang, Biing Hwang ^a  

^a GEORGIA INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

Non uniform error cost; Weighted MCE

Indexed keywords

(SIM+SME) TRAINING METHOD; AUTOMATIC SPEECH RECOGNITION (ASR); BAYES DECISION THEORY; CLASSIFIER DESIGNS; DECISION RULES; ERROR RATE (ER); KEYWORD SPOTTING SYSTEMS; LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION (LVCSR); MINIMUM CLASSIFICATION ERROR (MCE); NON-UNIFORM ERROR; OBJECTIVE FUNCTION (OF); PATTERN RECOGNITION PROBLEMS; PERFORMANCE METRIC; PRACTICAL APPLICATIONS; RECOGNITION ERRORS; STATISTICAL PATTERN RECOGNITION APPROACH; SYSTEM PERFORMANCES; TRAINING ALGORITHMS;

ADMINISTRATIVE DATA PROCESSING; ALGORITHMS; ARCHITECTURAL DESIGN; BOOLEAN FUNCTIONS; CLASSIFICATION (OF INFORMATION); COMPUTER NETWORKS; CONTINUOUS SPEECH RECOGNITION; DECISION MAKING; DECISION SUPPORT SYSTEMS; DECISION THEORY; ERROR ANALYSIS; EVOLUTIONARY ALGORITHMS; FEATURE EXTRACTION; FUNCTION EVALUATION; GAME THEORY; MANAGEMENT INFORMATION SYSTEMS; MICROFLUIDICS; MULTITASKING; OBJECT RECOGNITION; OPERATIONS RESEARCH; PATTERN RECOGNITION; PATTERN RECOGNITION SYSTEMS; SCHEDULING ALGORITHMS; SPEECH; SPEECH ANALYSIS; SPEECH PROCESSING;

SPEECH RECOGNITION;

EID: 44849124203     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (10)

1. R. Duda, P. Hart, and D. Stork, Pattern Classification. New York, NY: John Wiley, 2001, 2nd edition.
2. B.-H. Juang, W, Chou, and C.-H. Lee, "Minimum classification error rate methods for speech recognition," IEEE Transactions on Speech and Audio Processing, vol. 5, pp. 257-265, May 1997.
3. W Macherey, L. Haferkamp, R. Schluter, and H. Ney, "Investigations on error minimizing training criteria for discriminative training in automatic speech recognition," in Interspeech-2005, Lisbon, Portugal, Sep. 2005, pp. 2133-2136.
4. R. Schluter, W. Macherey, B. Muller, and H. Ney, "Comparison of discriminative training criteria and optimization methids for speech recognition," Speech Communication, vol. 34, no. 1, pp. 287-310, May. 200.1.
5. Y. Normandin, "Hidden markov models, maximum mutual infomation estimation, and the speech recognition problem," Ph.D. dissertation, McGill University, Montreal, Canada, 1991.
6. D. Povey, "Discriminative training for large vocabulary speech recognition," Ph.D. dissertation, Cambridge University, Cambridge, Britain, Jul. 2004.
7. D. S. Pallet, J. G. Fiscus, W. M. Fisher, J. S. Garofolo, B. A. Lund, and M. A. Przybocki, "1994 benchmark test for the arpa spoken language program," in ARPA Human language Technology Workshop, Austin, Texas, Jan. 1995, pp. 5-36.
8. L. R. Rabiner and B. H. Juang, Fundamentals of Speech Recognition. Englewood Cliffs, NJ: Prentice-Hall, 1993.
9. Q. Fu, A.Moreno, B. H. Juang, J.-L. Zhou, and F.Soong, "Generalization of the minimum classification error (mce) training based on maximizing generalized posterior probability (gpp)," in ICSLP-2006, Pittsburgh, PA, Sep. 2006.
10. P. C. Woodland, J. J. Odell, V. Valtchev, and S. J. Young, "Large vocabulary continuous speech recognition using htk," in Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Adelaide, Australia, Apr. 1994, pp. 125-128.