Maximum mutual information estimation with unlabeled data for phonetic classification

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Volumn , Issue , 2008, Pages 952-955

  Huang, Jui Ting ^a   Hasegawa Johnson, Mark ^a  

^a University of Illinois at Urbana Champaign   (United States)

Author keywords

Gaussian mixture models; Maximum mutual information; Unlabeled speech

Indexed keywords

ERROR RATE; GAUSSIAN MIXTURE MODEL; LABELED AND UNLABELED DATA; LABELED DATA; MAXIMUM MUTUAL INFORMATION; MAXIMUM MUTUAL INFORMATION ESTIMATIONS; ML ESTIMATE; PHONETIC CLASSIFICATION; REDUCTION OF ERRORS; TRAINING FRAMEWORK; TRAINING OBJECTIVES; UNLABELED DATA; UNLABELED SPEECH;

BLIND SOURCE SEPARATION; LINGUISTICS; MAXIMUM LIKELIHOOD ESTIMATION; STEREOPHONIC BROADCASTING;

SPEECH COMMUNICATION;

EID: 84867218563     PISSN: None     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (13)

1. Y. Normandin, "Hidden markov models, maximum mutual information estimation, and the speech recognition problem," Ph.D. dissertation, Montreal, Que., Canada, Canada, 1991.
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, no. 3, pp. 257-265, 1997.
3. D. Povey and P. Woodland, "Minimum phone error and i-smoothing for improved discriminative training," in Proc. IEEE Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1, 2002, pp. 105-108.
4. F. Sha and L. K. Saul, "Large margin hidden markov models for automatic speech recognition," in Advances in Neural Information Processing Systems 19, B. Schölkopf, J. Platt, and T. Hoffman, Eds. Cambridge, MA: MIT Press, 2007, pp. 1249-1256.
5. X. Zhu, "Semi-supervised learning literature survey," Computer Sciences, University of Wisconsin-Madison, Tech. Rep. 1530, 2005, http://www.cs.wisc.edu/~jerryzhu/pub/ssl-survey.pdf.
6. L. Lamel, J.-L. Gauvain, and G. Adda, "Lightly supervised and unsupervised acoustic model training," vol. 16, pp. 115-129, 2002.
7. F. Wessel and H. Ney, "Unsupervised training of acoustic models for large vocabulary continuous speech recognition," IEEE Transactions on Speech and Audio Processing, vol. 13, no. 1, pp. 23-31, Jan. 2005.
8. P. Gopalakrishnan, D. Kanevsky, A. Nadas, D. Nahamoo, and M. Picheny, "Decoder selection based on cross-entropies," in Proc. IEEE Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1, 1998, pp. 20-23.
9. D. Povey, "Discriminative training for large vocabulary speech recognition," Ph.D. dissertation, Cambridge University, 2003.
10. B. Merialdo, "Phonetic recognition using hidden markov models and maximum mutualinformation training," in Proc. IEEE Conference on Acoustics, Speech, and Signal Processing (ICASSP), vol. 1, 1988, pp. 111-114.
11. J. S. Garofolo, L. F. Lamel, W. M. Fisher, J. G. Fiscus, D. S. Pallett, and N. L. Dahlgren, "Darpa timit acoustic phonetic continuous speech corpus," 1993.
12. A. K. Halberstadt, "Heterogeneous acoustic measurements and multiple classifiers for speech recognition," Ph.D. dissertation, Massachusetts Institute of Technology, 1998.
13. T. Joachims, "Transductive inference for text classification using support vector machines," in Proceedings of ICML-99, 16th International Conference on Machine Learning, Bled, SL, 1999, pp. 200-209.