Backoff hierarchical class n-gram language models: effectiveness to model unseen events in speech recognition

Computer Speech and Language

Volumn 21, Issue 1, 2007, Pages 88-104

  Zitouni, Imed ^a  

^a IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

BACKOFF HIERARCHICAL CLASS; N-GRAM LANGUAGE MODELS; WALL STREET JOURNAL (WSJ);

COMPUTER PROGRAMMING LANGUAGES; PERFORMANCE; SPEECH RECOGNITION; VOCABULARY CONTROL;

HIERARCHICAL SYSTEMS;

EID: 33749854634     PISSN: 08852308     EISSN: 10958363     Source Type: Journal    
DOI: 10.1016/j.csl.2006.01.001     Document Type: Article

References (27)

1. Bahl, L., Brown, P., de Souza, P., Mercer, R., 1987. A tree-based statistical language model for natural language speech recognition. In: IEEE Transaction on Acoustics, Speech and Signal Processing, July, vol. 37, pp. 1001-1008.
2. Bai, S., Li, H., Lin, Z., Yuan, B., 1998. Building class-based language models with contextual statistics. In: Proceedings of the ICASSP - 1998.
3. Bellegarda J. Exploiting latent semantic information in statistical language modeling. Proceedings of the IEEE 88 8 (2000)
4. Bilmes, J.A., Kirchhoff, K., 2003. Factored language models and generalized parallel backoff. In: Proceedings of HLT/NAACL, Canada, May.
5. Breiman L., Friedman J., Olshen R., and Stone C. Classification and Regression Trees (1984), Wadsworth & Brooks
6. Brown P.F., DellaPietra V.J., DeSouza P.V., Lai J.C., and Mercer R.L. Class-based n-gram models of natural language. Computational Linguistics 18 4 (1992) 467-479
7. Cover T.M., and Thomas J.A. Elements of Information Theory (1991), Wiley and Sons
8. Cover, T.M., Hart, P.E., 1967. Nearest neighbor pattern classification. In: IEEE Transaction on Information Theory, vol. 13, pp. 21-27.
9. Darken, C., Moody, J., 1990. Fast adaptive k-means clustering: some empirical results. In: International Joint Conference on Neural Networks, vol. 2, pp. 233-238.
10. Dupont, P., Rosenfeld, R., 1997. Lattice based language models. Technical Reports CMU-CS-97-173, Carnegie Mellon University.
11. Gupta V., Lenning M., and Mermelstein P. A language model for very large vocabulary speech recognition. Computer Speech and Language (1992) 331-344
12. Goodman J. A bit of progress in language modeling. Computer Speech and Language October (2001) 403-434
13. Heeman, P.A., 1999. Pos tags and decision trees for language modeling. In: Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora, College Park, MD, pp. 129-137.
14. Jelinek F. Self-organized language modeling for speech recognition. In: Waibel A., and Lee K.-F. (Eds). Readings in Speech Recognition (1990), Morgan Kaufmann, San Mateo, CA 450-506
15. Katz S.M. Estimation of probabilities from sparse data for the language model component of a speech recognizer. IEEE Transactions on Acoustic, Speech, and Signal Processing 35 3 (1987)
16. Li, H., Haton, J.P., Su, J., Gong, Y., 1995. Speaker recognition with temporal transition models. In Eurospeech - 95, Madrid, Spain.
17. MacQueen J. Some methods for classification and analysis of multi-variate observations. In: LeCam L.M., and Neyman J. (Eds). Proceedings of the Fifth Berkeley Symposium on Mathematics, Statistics and Probability vol. 281 (1967), U. California Press, Berkeley
18. Miller, J.W., Alleva, F., 1996. Evaluation of a language model using a clustered model backoff. In Proceedings of the ICSLP - 1996.
19. Rosenfeld R. Two decades of statistical language modeling: where do we go from here?. Proceedings of the IEEE 88 8 (2000)
20. Samuelsson, C., Reichl, W., 1999. A class-based language model for large-vocabulary speech recognition extracted from part-of-speech statistics. In: Proceedings of the ICASSP - 1999.
21. Suhm, B., Waibel, W., 1994. Towards better language models for spontaneous speech. In: Proceedings of the ICSLP - 1994.
22. Xu, P., Jelinek, F., 2004. Random forests in language modeling. In: Conference on Empirical Methods in Natural Language Processing.
23. Zitouni I., and Kuo H.J. Effectiveness of the backoff hierarchical class n-gram language models to model unseen events in speech recognition. Proceedings of the IEEE ASRU - 2003 (2003), St. Thomas, US Virgin Islands
24. Zitouni, I., Siohan, O., Kuo, H.-K.J., Lee, C.-H., 2002. Backoff hierarchical class n-gram language modelling for automatic speech recognition systems. In: Proceedings of the ICSLP - 2002, Denver, USA.
25. Zitouni, I., Siohan, O., Lee, C.-H., 2003a. Hierarchical class n-gram language models: towards better estimation of unseen events in speech recognition. In: Proceedings of the Eurospeech - 2003, Geneva, Switzerland.
26. Zitouni, I., Zhou, Q., Li, Q.P., 2003b. A hierarchical approach for better estimation of unseen event likelihood in speech recognition. In: Proceedings of the IEEE NLPKE - 2003, Beijing, China.
27. Zhou, Q., Chou, W., 1997. An approach to continuous speech recognition based on self-adjusting decoding graph. In: Proceedings of the ICASSP - 1997, pp. 1779-1782.