Cross-validation and aggregated EM training for robust parameter estimation

Computer Speech and Language

Volumn 22, Issue 2, 2008, Pages 185-195

  Shinozaki, Takahiro ^a   Ostendorf, Mari ^b  

^a KYOTO UNIVERSITY   (Japan)

^b University of Washington   (United States)

Author keywords

Cross validation; EM training; HMM; Overtraining; Sufficient statistics

Indexed keywords

ALGORITHMS; COST ACCOUNTING; ERROR ANALYSIS; PARAMETER ESTIMATION; PERSONNEL TRAINING;

CROSS-VALIDATION; OVERTRAINING; SUFFICIENT STATISTICS;

ROBUST CONTROL;

EID: 35549000218     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2007.07.005     Document Type: Article

References (21)

1. Anguera, X., Shinozaki, T., Wooters, C., Hernando, J., 2007. Model complexity selection and cross-validation EM training for robust speaker diarization. In: ICASSP, vol. IV. Hawaii, pp. 273-276.
2. Bahl, L.R., Brown, P.F., de Souza, P.V., Mercer, R.L., 1986. Maximum mutual information estimation of hidden Markov model parameters for speech recognition. In: Proceedings of the ICASSP. pp. 49-52.
3. Breiman L. Bagging predictors. Machine Learning 24 2 (1996) 123-140
4. Chen, S., Gopalakrishnan, P.S., 1998. Clustering via the Bayesian Information Criterion with applications in speech recognition. In: Proceedings of the ICASSP. pp. 645-648.
5. Dempster A.P., Laird N.M., and Rubin D.B. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society Series B 39 1 (1977) 1-38
6. Gunawardana A., and Byrne W. Convergence theorems for generalized alternating minimization procedures. Journal of Machine Learning Research 6 (2005) 2049-2073
7. Günter, S., Bunke, H., 2002. A new combination scheme for HMM-based classifiers and its application to handwriting recognition. In: Proceedings of the International Conference on Pattern Recognition, vol. II. pp. 332-337.
8. Hastie T., Tibshirani R., and Friedman J. The Elements of Statistical Learning (2001), Springer-Verlag
9. Hwang, M.Y., Lei, X., Wang, W., Shinozaki, T., 2006. Investigation on Mandarin broadcast news speech recognition. In: Proceedings of the ICSLP. pp. 1233-1236.
10. Jia, Y., Yan, Y., Yuan, B., 2000. Dynamic thresholds setting via Bayesian information criteria in HMM training. In: Proceedings of the ICSLP, vol. IV. pp. 169-171.
11. Leggetter, C.J., Woodland, P.C., 1995. Flexible speaker adaptation using maximum likelihood linear regression. In: Proceedings of the Eurospeech. pp. 1155-1158.
12. Melin, H., Koolwaaij, J.W., Lindberg, J., Bimbot, F., 1998. A comparative evaluation of variance flooring techniques in HMM-based speaker verification. In: Proceedings of the ICSLP. Sydney, pp. 2379-2382.
13. Nigam, K., Chani, R., 2000. Analyzing the effectiveness and applicability of co-training. In: CIKM. pp. 86-93.
14. Povey, D., Woodland, P., 2002. Minimum phone error and i-smoothing for improved discriminative training. In: Proceedings of the ICASSP, vol. I. pp. 105-108.
15. Rogina, I., 1997. Automatic architecture design by likelihood-based context clustering with crossvalidation. In: Proceedings of the Eurospeech. Rhodes, Greece, pp. 1223-1226.
16. Shinoda, K., Watanabe, T., 1997. Acoustic modeling based on the MDL criterion for speech recognition. In: Proceedings of the EuroSpeech, vol. 1. pp. 99-102.
17. Shinozaki, T., 2006. HMM state clustering based on efficient cross-validation. In: Proceedings of the ICASSP, vol. I. Toulouse, pp. 1157-1160.
18. Shinozaki, T., Ostendorf, M., 2007. Cross-validation EM training for robust parameter estimation. In: ICASSP, vol. IV. Hawaii, pp. 437-440.
19. Siohan, O., Ramabhadran, B., Kingsbury, B., 2005. Constructing ensembles of ASR systems using randomized decision trees. In: Proceedings of the ICASSP, vol. 1. pp. 197-200.
20. Soltau, H., Kingsbury, B., Mangu, L., Povery, D., Saon, G., Zweig, G., 2005. The IBM 2004 conversational telephony system for rich transcription. In: Proceedings of the ICASSP, vol. I. pp. 205-208.
21. Young S., Evermann G., Gales M., Hain T., Kershaw D., Liu X., Moore G., Odell J., Ollason D., Povey D., Valtchev V., and Woodland P. The HTK Book (for HTK Version 3.4) (2006), Cambridge University Engineering Department