Discriminative training based on an integrated view of MPE and MMI in margin and error space

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn , Issue , 2010, Pages 4894-4897

  McDermott, Erik ^a   Watanabe, Shinji ^a   Nakamura, Atsushi ^a  

^a NTT Communication Science Laboratories   (Japan)

Author keywords

Discriminative training; Speech recognition

Indexed keywords

E-LEARNING; ERROR STATISTICS;

DISCRIMINATIVE TRAINING; FLEXIBLE CONTROL; FORWARD / BACKWARD ALGORITHMS; FUNCTIONALS; MAXIMUM MUTUAL INFORMATION; MINIMUM PHONE ERROR; OBJECTIVE FUNCTIONS; RECOGNITION ERROR; SIMPLE++; WEIGHTED OBJECTIVE FUNCTION;

SPEECH RECOGNITION;

EID: 78049409757     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2010.5495106     Document Type: Conference Paper

References (15)

1. X. Li, H. Jiang, and C. Liu, "Large margin HMMs for speech recognition," in Proc. ICASSP, 2005, vol. 5, pp. 513-516.
2. J. Li, Z.-J. Yan, C.-H. Lee, and R.-H. Wang, "A study on soft margin estimation for LVCSR," in Proc. ASRU, 2007, pp. 268-271.
3. D. Yu, L. Deng, X. He, and A. Acero, "Large-margin Minimum Classification Error training: A theoretical risk perspective," in Computer Speech and Language, 2008, vol. 22, pp. 415-429.
4. F. Sha and L. K. Saul, "Large margin hidden Markov models for automatic speech recognition," in Proc. of NIPS, 2007, pp. 1249-1456.
5. D. Povey and P.C. Woodland, "Minimum Phone Error and I-smoothing for improved discriminative training," in Proc. ICASSP, 2002, vol. 1, pp. 105-108.
6. G. Saon and D. Povey, "Penalty Function Maximization for Large Margin HMM Training," in Proc. Interspeech, 2008, pp. 920-923.
7. G. Heigold, T. Deselaers, R. Schlueter, and H. Ney, "Modified MMI/MPE: a Direct Evaluation of the Margin in Speech Recognition," in Proc. ICML, 2008, vol. 307, pp. 384-391.
8. E. McDermott, S. Watanabe, and A. Nakamura, "Margin-Space Integration of MPE Loss via Differencing of MMI Functionals for Generalized Error-Weighted Discriminative Training," in Proc. Interspeech, 2009, pp. 224-227.
9. J. Zheng and A. Stolcke, "Improved Discriminative Training Using Phone Lattices," in Proc. Interspeech, 2005, pp. 2125-2128.
10. E. McDermott and A. Nakamura, "Flexible Discriminative Training Based On Equal Error Group Scores Obtained From An Error-Indexed Forward-Backward Algorithm," in Proc. Interspeech, 2008, pp. 2398-2401.
11. A. Nakamura, E. McDermott, S. Watanabe, and S. Katagiri, "A Unified View for Discriminative Objective Functions Based on Negative Exponential of Difference Measure Between Strings," in Proc. ICASSP, 2009, pp. 1633-1636.
12. 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, no. 1, pp. 203-223, January 2007.
13. H.-A. Chang and J. R. Glass, "Discriminative Training of Hierarchical Acoustic Models for Large Vocabulary Continuous Speech Recognition," in Proc. ICASSP, 2009, pp. 4481-4484.
14. T. Jebara, Machine Learning: Discriminative and Generative, Kluwer Academic, 2004.
15. E. McDermott, S. Watanabe, and A. Nakamura, "Practical Integration of Minimum Phone Error in Margin Space using Maximum Mutual Information Building Blocks for Discriminative Training," in Proc. Acoustical Society of Japan, March 2010, Spring meeting.