Discriminative training of acoustic models for system combination

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

Volumn , Issue , 2013, Pages 2355-2359

  Tachioka, Yuuki ^a   Watanabe, Shinji ^b  

^a MITSUBISHI ELECTRIC CORPORATION   (Japan)

^b MITSUBISHI ELECTRIC RESEARCH LABORATORIES   (United States)

Author keywords

Boosting; Discriminative training; Margin training; MMI; System combination

Indexed keywords

COMPUTER APPLICATIONS; COMPUTER SIMULATION;

AUTOMATIC SPEECH RECOGNITION; BOOSTING; COMPLEMENTARY SYSTEMS; CONVENTIONAL SYSTEMS; DISCRIMINATIVE TRAINING; MMI; NOISY SPEECH RECOGNITION; SYSTEM COMBINATION;

SPEECH RECOGNITION;

EID: 84893695671     PISSN: 2308457X     EISSN: 19909772     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (30)

1. J. Baker, L. Deng, J. Glass, S. Khudanpur, C. Lee, N. Morgan, and D. O'Shaughnessy, "Research developments and directions in speech recognition and understanding part 1, " IEEE Signal Processing Magazine, vol. 26, pp. 75-80, 2009. 5.
2. X. He, L. Deng, and W. Chou, "Discriminative learning in sequential pattern recognition, " IEEE Signal Processing Magazine, vol. 25, pp. 14-36, 2008. 9.
3. L. Bahl, P. Brown, P. de Souza, and R. Mercer, "Maximum mutual information estimation of hidden Markov model parameters for speech recognition, " in Proceedings ICASSP, vol. 11, pp. 49-52, 1986.
4. D. Povey and P. Woodland, "Minimum phone error and Ismoothing for improved discriminative training, " in Proceedings ICASSP, vol. I, pp. 105-108, 2002.
5. E. McDermott, T. J. Hazen, J. Le Roux, A. Nakamura, and S. Katagiri, "Discriminative training for large-vocabulary speech recognition using minimum classification error, " IEEE Transactions on Audio, Speech, and Language Processing, vol. 15, pp. 203-223, 2007. 1.
6. E. McDermott, S. Watanabe, and A. Nakamura, "Discriminative training based on an integrated view of MPE and MMI in margin and error space, " in Proceedings ICASSP, pp. 4894-4897, 2010.
7. G. Heigold, H. J. Ney, R. Schl̈uter, and S. Wiesler, "Discriminative training for automatic speech recognition: Modeling, criteria, optimization, implementation, and performance, " IEEE Signal Processing Magazine, vol. 29, pp. 58-69, 2012. 11.
8. M. Gales, S. Watanabe, and E. Fosler-Lussier, "Structured discriminative models for speech recognition: An overview, " IEEE Signal Processing Magazine, vol. 29, pp. 70-81, 2012. 11.
9. J. Fiscus, "A post-processing system to yield reduced error word rates: Recognizer output voting error reduction (ROVER), " in Proceedings ASRU, pp. 347-354, 1997.
10. G. Evermann and P. Woodland, "Posterior probability decoding, confidence estimation and system combination, " in Proceedings NIST Speech Transcription Workshop, 2000.
11. B. Hoffmeister, T. Klein, R. Schlüter, and H. Ney, "Frame based system combination and a comparison with weighted ROVER and CNC, " in Proceedings ICSLP, pp. 537-540, 2006.
12. T. Shinozaki and S. Furui, "Strategies for model training and adaptation based on data dependency control, " APSIPA Overview, 2011.
13. O. Siohan, B. Ramabhadran, and B. Kingsbury, "Constructing ensembles of ASR systems using randomized decision trees, " in Proceedings ICASSP, pp. 197-200, 2005.
14. C. Breslin and M. Gales, "Generating complementary systems for speech recognition, " in Proceedings ICASSP, pp. 337-340, 2007.
15. H. Tang, M. Hasegawa-Johnson, and T. S. Huang, "Toward robust learning of the Gaussian mixture state emission densities for hidden Markov models, " in Proceedings ICASSP, pp. 5242-5245, 2010.
16. G. Saon and H. Soltau, "Boosting systems for LVCSR, " in Proceedings INTERSPEECH, pp. 1341-1344, 2010.
17. Y. Freund and R. Schapire, "A dicision-theoretic generalisation of online learning and an application to boosting, " Journal of Computer and System Sciences, vol. 55, pp. 119-139, 1997. 8.
18. P. Viola and M. Jones, "Robust real-time object detection, " in Proceedings Second International Workshop on Statistical and Computational Theories of Vision - Modeling, Learning, Computing, and Sampling, pp. 1-25, 2001. 7.
19. J. Friedman, T. Hestie, and R. Tibshirani, "Additive logistic regression: A statistical view of boosting, " Annals of Statistics, vol. 28, pp. 337-407, 2000.
20. D. Povey, D. Kanevsky, B. Kingsbury, B. Ramabhadran, G. Saon, and K. Visweswariah, "Boosted MMI for model and feature-space discriminative training, " in Proceedings ICASSP, pp. 4057-4060, 2008.
21. Y. Normandin and S. D. Morgera, "An improved MMIE training algorithm for speaker-independent, small vocabulary, continuous speech recognition, " in Proceedings ICASSP, vol. 1, pp. 537-540, 1991.
22. E. Vincent, J. Barker, S. Watanabe, J. Le Roux, F. Nesta, and M. Matassoni, "The second 'CHiME' speech separation and recognition challenge: Datasets, tasks and baselines, " in Proceedings ICASSP, 2013.
23. D. Povey, A. Ghoshal, G. Boulianne, L. Burget, O. Glembek, N. Goel, M. Hannemann, M. Petr, Y. Qian, P. Schwarz, J. Silovský, G. Stemmer, and K. Veselý, "The Kaldi speech recognition toolkit, " in Proceedings ASRU, pp. 1-4, 2011.
24. Y. Tachioka, S. Watanabe, J. Le Roux, and J. Hershey, "Discriminative methods for noise robust speech recognition: A CHiME challenge benchmark, " The 2nd International Workshop on Machine Listening in Multisource Environments, 2013.
25. Y. Tachioka, S. Watanabe, and J. Hershey, "Effectiveness of discriminative training and feature transformation for reverberated and noisy speech, " in Proceedings ICASSP, 2013.
26. R. Haeb-Umbach and H. Ney, "Linear discriminant analysis for improved large vocabulary continuous speech recognition, " in Proceedings ICASSP, pp. 13-16, 1992.
27. R. Gopinath, "Maximum likelihood modeling with Gaussian distributions for classification, " in Proceedings ICASSP, pp. 661- 664, 1998.
28. M. Gales, "Semi-tied covariance matrices for hidden Markov models, " IEEE Transactions on Speech and Audio Processing, vol. 7, pp. 272-281, 1999. 3.
29. T. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul, "A compact model for speaker-adaptive training, " in Proceedings ICSLP, pp. 1137-1140, 1996.
30. M. Gales, "Maximum likelihood linear transformations for HMM-based speech recognition, " Computer Speech and Language, vol. 12, pp. 75-98, 1998.