On the choice of classes in MCE based discriminative HMM-Training for speech recognizers used in the telephone environment

EUROSPEECH 2001 - SCANDINAVIA - 7th European Conference on Speech Communication and Technology

Volumn , Issue , 2001, Pages 1633-1636

  Bauer, Josef G ^a  

^a SIEMENS AG   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

MARKOV PROCESSES; SPEECH; SPEECH COMMUNICATION; SPEECH RECOGNITION; TELEPHONE SETS; VOCABULARY CONTROL;

CONNECTED DIGITS; DISCRIMINATIVE APPROACH; ISOLATED WORD RECOGNITION; LETTER RECOGNITION; MINIMUM CLASSIFICATION ERROR; SPEECH RECOGNIZER; WORD ERROR RATE; WORD RECOGNITION;

HIDDEN MARKOV MODELS;

EID: 0013269126     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (9)

1. Biing-Hwang Juang, Wu Chou, and Chin-Hui Lee, "Minimum classification error rate methods for speech recognition, " IEEE Transactions on Speech and Audio Processing, vol. 5, no. 3, pp. 257-265, 1997.
2. Josef G. Bauer, "Enhanced control and estimation of parameters for a telephone based isolated digit recognizer, " in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 1997, pp. 1531-1534.
3. Josef G. Bauer, "Application of discriminative methods for isolated word recognition, " in Classification, Data Analysis and Data Highways, I. Balderjahn, R. Mathar, and M. Schader, Eds. 1998, pp. 287-294, Springer.
4. D. Povey and P. C. Woodland, "Frame discrimination training of hmms for large vocabulary speech recognition, " in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 1999, pp. 333-336.
5. W. Reichl and G. Ruske, "Discriminative training for continuous speech recognition, " in Proc. European Conference on Speech Communication and Technology (Eurospeech), 1995, pp. 537-540.
6. Erik McDermott and Shigeru Karagiri, "String-level mce for continuous phoneme recognition, " in EUROSPEECH, 1997, pp. 123-1236.
7. W. Chou, C.-H. Lee, and B.-H. Juang, "Minimum error rate training based on n-best string models, " in Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP), 1993, pp. 652-655.
8. "Elra web site, " http://www.icp.grenet.fr/ELRA.
9. Josef G. Bauer and Jochen Junkawitsch, "Accurate recognition of city names with spelling as a fall back strategy, " in Proc. European Conference on Speech Communication and Technology (Eurospeech), 1999, vol. 1, pp. 263-266.