Self-supervised discriminative training of statistical language models

Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2009

Volumn , Issue , 2009, Pages 317-322

  Xu, Puyang ^a   Karakos, Damianos ^a   Khudanpur, Sanjeev ^a  

^a Whiting School of Engineering   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

AUTOMATIC SPEECH RECOGNITION; DISCRIMINATIVE TRAINING; EMPIRICAL RESULTS; EXPONENTIAL FORM; LANGUAGE MODEL; LARGE VOCABULARY; LIKELIHOOD RATIOS; MAXIMUM ENTROPY; MODEL PARAMETERS; STATISTICAL LANGUAGE MODELS; TEXT CORPORA;

COMPUTATIONAL LINGUISTICS; MAXIMUM LIKELIHOOD ESTIMATION; REMELTING;

SPEECH RECOGNITION;

EID: 77949367510     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2009.5373401     Document Type: Conference Paper

References (14)

1. F. Jelinek, Statistical Methods for Speech Recognition. MIT Press, 1998.
2. S. F. Chen and J. Goodman, "An empirical study of smoothing techniques for language modeling," in Proceedings of the 34th Annual Meeting of the ACL, 1996, pp. 310-318.
3. B.Roark, M.Saraclar, and M.Colins, "Corrective language modeling for large vocabulary asr with the perceptron algorithm," in Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Quebec, Canada, May 2004, pp. 749-752.
4. B.Roark, M.Saraclar, M.Colins, and M.Johnson, "Discriminative language modeling with conditional random fields and the perceptron algorithm," in Proc. the 42nd Annual Meeting of the Association for Computational Linguistics (ACL), Barcelona, Spain, Jul. 2004, pp. 47-54.
5. D. Jurafsky and J. H. Martin, Speech and Language Processing. Prentice Hall, 2000.
6. N. A. Smith and J. Eisner, "Contrastive estimation: Training log-linear models on unlabeled data," in Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL), Ann Arbor, Michigan, June 2005, pp. 354-362.
7. L. Mangu, E. Brill, and A. Stolcke, "Finding consensus among words: Lattice-based word error minimization," in Proc. Eurospeech, 1999, pp. 495-498.
8. J. Fiscus, "A post-processing system to yield reduced word error rates: Recogniser output voting error reduction (ROVER)," in Proc. 1997 IEEE Workshop on Automatic Speech Recognition and Understanding, Santa Barbara, CA, 1997, pp. 347-352.
9. R.Rosenfeld, "A maximum entropy approach to adaptive statistical language modeling," Computer Speech and Language, vol. 10, pp. 187-228, Mar. 1996.
10. M.Colins, M.Saraclar, and B.Roark, "Discriminative syntactic language modeling for speech recognition," in Proc. the 43rd Annual Meeting of the Association for Computational Linguistics (ACL), Sydney, Australia, Jun. 2005, pp. 507-514.
11. S. F. Chen and R. Rosenfeld, "A Gaussian prior for smoothing maximum entropy models," Tech. Rep., 1999.
12. J.Darroch and D.Ratcliff, "Generalized iterative scaling for log-linear models," The Annals of Mathematical Statistics, vol. 24, pp. 413-421, 1972.
13. W. Wang and M. P. Harper, "The SuperARV language model: Investigating the effectiveness of tightly integrating multiple knowledge sources," in Proc. the Conference on Empirical Methods in Natural Language Processing (EMNLP), Philadelphia, Jul. 2002, pp. 238-247.
14. J. Wu and S. Khudanpur, "Efficient training methods for maximum entropy language modeling," in Proc. the 6th International Conference on Spoken Language Technologies (ICSLP-00, 2000, pp. 114-117.