Error approximation and minimum phone error acoustic model estimation

IEEE Transactions on Audio, Speech and Language Processing

Volumn 18, Issue 6, 2010, Pages 1269-1279

  Gibson, Matthew ^a   Hain, Thomas ^b  

^a UNIVERSITY OF CAMBRIDGE   (United Kingdom)

^b UNIVERSITY OF SHEFFIELD   (United Kingdom)

Author keywords

Acoustic modeling; discriminative training; minimum phone error

Indexed keywords

ACOUSTIC MODEL; ACOUSTIC MODELING; DISCRIMINATIVE TRAINING; EDIT DISTANCE; ERROR APPROXIMATIONS; ERROR CALCULATIONS; ERROR METRICES; EXPERIMENTAL EVALUATION; MINIMUM PHONE ERROR; PERFORMANCE IMPROVEMENTS; VOCABULARY RECOGNITION;

ERRORS; PARAMETER ESTIMATION; SPEECH RECOGNITION;

TELEPHONE SETS;

EID: 77955783938     PISSN: 15587916     EISSN: None     Source Type: Journal    
DOI: 10.1109/TASL.2009.2032607     Document Type: Article

References (30)

1. B.-H. Juang and S. Katagiri, "Discriminative learning for minimum error classification," IEEE Trans. Signal Process., vol.40, no.12, pp. 3043-3054, Dec. 1992.
2. P. Woodland and D. Povey, "Large scale discriminative training of hidden Markov models for speech recognition," Comput. Speech Lang., vol.16, no.1, pp. 25-37, 2002.
3. D. Povey, "Discriminative training for large vocabulary speech recognition," Ph.D. dissertation, Cambridge Univ., Cambridge, U.K., 2003.
4. J. Kaiser, B. Horvat, and Z. Kacic, "Overall risk criterion estimation of hidden Markov model parameters," Speech Commun., vol.38, no.3-4, pp. 383-398, 2002.
5. G. Heigold, W. Macherey, R. Schluter, and H. Ney, "Minimum exact word error training," in Proc. ASRU, 2005, pp. 186-190.
6. K. Na, B. Jeon, D. Chang, S. Chae, and S. Ann, "Discriminative training of hidden Markov models using overall risk criterion and reduced gradient descent method," in Proc. Eurospeech, Madrid, Spain, 1995, pp. 97-100.
7. P. Gopalakrishnan, D. Kanevsky, A. Nadas, and D. Nahamoo, "A generalization of the Baum algorithm to rational objective functions," in Proc. ICASSP, Glasgow, U.K., 1989, pp. 631-634.
8. Y. Normandin, "Hidden Markov models, maximum mutual information estimation and the speech recognition problem," Ph.D. dissertation, McGill Univ., Montreal, QC, Canada, 1991.
9. D. Povey, M. Gales, D. Y. Kim, and P. Woodland, "MMI-MAP and MPE-MAP for acoustic model adaptation," in Proc. Eurospeech, Geneva, Switzerland, 2003, pp. 1981-1984.
10. D. Kanevsky, "Extended Baum transformations for general functions," in Proc. ICASSP, 2004, vol.1, pp. 821-824.
11. M. Gibson, "Minimum Bayes risk acoustic model estimation and adaptation," Ph.D. dissertation, Sheffield Univ., Sheffield, U.K., 2008.
12. D. Povey and P. Woodland, "Minimum phone error and I-smoothing for improved discriminative training," in Proc. ICASSP, Orlando, FL, 2002, pp. 105-108.
13. S. Young, G. Everman, T. Hain, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P. Woodland, The HTK Book for HTK Version 3.2.1, 2003.
14. V. Valtchev, J. Odell, P. Woodland, and S. Young, "MMIE training of large vocabulary recognition systems," Speech Commun., vol.22, no.4, pp. 303-314, 1997.
15. R. Schluter, W. Macherey, S. Kanthak, H. Ney, and L. Welling, "Comparison of optimization methods for discriminative training criteria," in Proc. Eurospeech, 1997, pp. 15-18.
16. R. Schluter, B. Muller, F. Wessel, and H. Ney, "Interdependence of language models and discriminative training," in Proc. IEEE ASRU Workshop, Keystone, CO, 1999, pp. 119-122.
17. J. Zheng and A. Stolcke, "Improved discriminative training using phone lattices," in Proc. Interspeech, Lisbon, Portugal, 2005, pp. 2125-2128.
18. V. Goel, S. Kumar, and W. Byrne, "Segmental minimum Bayes-risk decoding for automatic speech recognition," IEEE Trans. Speech Audio Process., vol.12, no.3, pp. 234-249, May 2004.
19. V. Doumpiotis and W. Byrne, "Lattice segmentation and minimum Bayes risk discriminative training for large vocabulary continuous speech recognition," Speech Commun., vol.48, no.2, pp. 142-160, 2005.
20. T. Hain, L. Burget, J. Dines, G. Garau, M. Karafiat, M. Lincoln, I. McCowan, D. Moore, V. Wan, R. Ordelman, and S. Renals, "The 2005 AMI system for the transcription of speech in meetings," in Proc. MLMI, 2005.
21. T. Hain, L. Burget, J. Dines, I. McCowan, G. Garau, M. Karafiat, M. Lincoln, D. Moore, V. Wan, R. Ordelman, and S. Renals, "The development of the AMI system for the transcription of speech in meetings," in Proc. MLMI, 2005.
22. L. Lee and R. Rose, "Speaker normalization using efficient frequency warping procedures," in Proc. ICASSP, Atlanta, GA, 1996, vol.1, pp. 353-356.
23. B. S. Atal, "Effectiveness of linear prediction characteristics of the speech wave for automatic speaker identification and verification," J. Acoust. Soc. Amer., vol.6, pp. 1304-1312, 1974.
24. S. Fitt, "Documentation and User Guide to UNISYN Lexicon and Post-Lexical Rules," Centre for Speech Technology Research, Edinburgh Univ., Edinburgh, U.K., 2000, Tech. Rep.
25. P. Woodland, M. Gales, D. Pye, and S. Young, "Broadcast news transcription using HTK," in Proc. ICASSP, Munich, Germany, 1997, vol.2, pp. 719-722.
26. L. Burget, "Combination of speech features using smoothed het-eroscedastic linear discriminant analysis," in Proc. Interspeech, Jeju Island, Korea, 2004, pp. 2549-2552.
27. F. Wessel, R. Schluter, and H. Ney, "Explicit word error minimization using word hypothesis posterior probabilities," in Proc. ICASSP, Salt Lake City, UT, 2001, pp. 33-36.
28. J. Steiger, "Tests for comparing elements of a correlation matrix," Psychological Bull., vol.87, pp. 245-251, 1980.
29. L. Gillick and S. Cox, "Some statistical issues in the comparison of speech recognition algorithms," in Proc. ICASSP, Philadelphia, PA, 1989, pp. 532-535.
30. D. S. Pallett, W. M. Fisher, and J. Fiscus, "Tools for the analysis of benchmark speech recognition tests," in Proc. ICASSP, Albuquerque, NM, 1990, pp. 97-100.