Discriminative feature transforms using differenced maximum mutual information

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

Volumn , Issue , 2012, Pages 4753-4756

  Delcroix, Marc ^a   Ogawa, Atsunori ^a   Watanabe, Shinji ^a,b   Nakatani, Tomohiro ^a   Nakamura, Atsushi ^a  

^a NTT Communication Science Laboratories   (Japan)

^b MITSUBISHI ELECTRIC RESEARCH LABORATORIES   (United States)

Author keywords

differenced MMI; discriminative feature transforms; discriminative training; Speech recognition

Indexed keywords

ACOUSTIC FEATURES; ACOUSTIC MODEL; DIFFERENCED MMI; DISCRIMINATIVE FEATURES; DISCRIMINATIVE TRAINING; FEATURE COMPENSATION; FEATURE TRANSFORM; FEATURE TRANSFORMATIONS; GAUSSIAN MIXTURE MODEL; GAUSSIANS; MAXIMUM MUTUAL INFORMATION; MINIMUM PHONE ERROR; NOISY SPEECH RECOGNITION; POSTERIOR PROBABILITY; RECOGNITION PERFORMANCE;

GAUSSIAN DISTRIBUTION; SIGNAL PROCESSING; STEREOPHONIC BROADCASTING;

SPEECH RECOGNITION;

EID: 84867593229     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICASSP.2012.6288981     Document Type: Conference Paper

References (16)

1. Nadas, A., Nahamoo, D. and Picheny, M. A., "On a model robust training method for speech recognition," IEEE Trans. ASSP, vol. 39, no. 9, pp. 1432 - 1435, 1988.
2. Povey, D. and Woodland, P., "Minimum phone error and I-smoothing for improved discriminative training," In Proc. ICASSP'02, vol. 1, pp. 105-108 , 2002.
3. Kuo, H.-K. J., Fosler-Lussier, E., Jiang, H. and Lee, C.-H., "Discriminative training of language models for speech recognition," In proc. ICASSP'02, vol.1, pp. 325-328, 2002.
4. Povey, D., "fMPE: discriminatively trained features for speech recognition," In Proc. ICASSP'05, pp. 961-964, 2005.
5. Droppo, J. and Acero, A., "Maximum mutual information SPLICE transform for seen and unseen conditions," In Proc. Interspeech'05, pp. 989-992, 2005.
6. Zhang, B., Matsoukas, S. and Schwartz, R., "Discriminatively trained region dependent transforms for speech recognition," In Proc. ICASSP'06, pp. 313-316, 2006.
7. Povey, D. , Kanevsky, D., Kingsbury, B., Ramabhadran, B., Saon, G. and Visweswariah, K., "Boosted MMI for model and feature-space discriminative training," In Proc. ICASSP'08, pp. 4057-4060, 2008.
8. Deng, L., Wu, J., Droppo, J. and Acero, A., "Analysis and comparison of two speech feature extraction/compensation algorithms," IEEE Signal Processing Letters, vol. 12, no. 6, pp. 477-480, 2005.
9. McDermott, E., Hazen, T.J., Le Roux, J., Nakamura, A. and Katagiri, S., "Discriminative training for large vocabulary speech recognition using Minimum Classification Error," IEEE Trans. ASLP, vol. 15, no. 1, pp. 203-223, 2007.
10. McDermott, E., Watanabe, S. and Nakamura, A., "Discriminative training based on an integrated view of MPE and MMI in margin and error space," In Proc. ICASSP'10, pp. 4894-4897, 2010.
11. Nakamura, A., McDermott, E., Watanabe, S. and Katagiri, S., "A unified view for discriminative objective functions based on negative exponential of difference measure between strings," In Proc. ICASSP'09, pp. 1633-1636, 2009.
12. Christensen, H., Barker, J., Ma, N., and Green, P., "The CHiME corpus: a resource and a challenge for computational hearing in multisource environments," In Proc. Interspeech'10, pp. 1918-1921, 2010.
13. Zheng, J. and Stolcke, A., "Improved discriminative training using phone lattices," In Proc. Interspeech'05, pp. 2125-2128, 2005.
14. Riedmiller, M. and Braun, H., "A direct adaptive method for faster backpropagation learning: The RPROP algorithm," In Proc. ICNN'93, pp. 586-591, 1993.
15. Nakatani, T., Araki, S., Delcroix, M., Yoshioka, T. and Fujimoto, M., "Reduction of highly nonstationary ambient noise based on spectral and locational characteristics of speech and noise for robust ASR," In Proc. Interspeech'11, 2011.
16. Hori, T., Hori, C., Minami, Y. and Nakamura, A., " Efficient-WFST-based one-pass decoding with on-the-fly hypothesis rescoring in extremely large vocabulary continuous speech recognition," IEEE Trans. ASLP, vol. 15, no. 4, pp. 1352-1365, 2007.