Adaptive language modeling with varied sources to cover new vocabulary items

IEEE Transactions on Speech and Audio Processing

Volumn 12, Issue 3, 2004, Pages 334-342

  Schwarm, Sarah E ^a   Bulyko, Ivan ^a   Ostendorf, Mari ^a  

^a University of Washington   (United States)

Author keywords

Language modeling; Mixture models; Speech recognition; Text normalization; Varied data sources

Indexed keywords

DATA REDUCTION; ERROR ANALYSIS; MATHEMATICAL MODELS; PROBABILITY; SPEECH RECOGNITION; VOCABULARY CONTROL;

LANGUAGE MODELING; MIXTURE MODELS; TEXT NORMALIZATION; VARIED DATA SOURCES;

SPEECH COMMUNICATION;

EID: 2442534985     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSA.2004.825666     Document Type: Article

References (30)

1. F. Jelinek, B. Merialdo, S. Roukos, and M. Strauss, "A dynamic LM for speech recognition," in Proc. ARPA Workshop on Speech and Natural Language, 1991, pp. 293-295.
2. R. Kuhn and R. de Mori, "A cache based natural language model for speech recognition," IEEE Trans. Pattern Anal. Machine Intell., pp. 570-583, 1992.
3. A. Kalai, S. Chen, A. Blum, and R. Rosenfeld, "On-line algorithms for combining language models," in Proc. ICASSP, 1999.
4. P. Witschel and H. Hoge, "Experiments in adaptation of language models for commercial applications," in Proc. Eurospeech, vol. 4, 1997, pp. 1967-1970.
5. R. Iyer and M. Ostendorf, "Transforming out-of-domain estimates to improve in-domain language models," in Proc. Eurospeech, vol. 4, 1997, pp. 1975-1978.
6. A. Rudnicky, "Language modeling with limited domain data," in Proc. ARPA Spoken Language Technology Workshop, 1995, pp. 66-69.
7. R. Iyer and M. Ostendorf, "Relevance weighting for combining multi-domain data for n-gram language modeling," Comput. Speech Lang., vol. 13, no. 3, pp. 267-282, 1999.
8. J. Bellegarda, "Exploiting both local and global constraints for multispan statistical language modeling," in Proc. ICASSP, 1998, pp. II:677-680.
9. M. Mahajan, D. Beeferman, and D. Huang, "Improved topic-dependent language modeling using information retrieval techniques," in Proc. ICASSP, 1999, pp. I:541-544.
10. R. Iyer and M. Ostendorf, "Modeling long range dependencies in languages," in Proc. ICSLP, 1996, pp. 236-239.
11. P. Clarkson and A. Robinson, "Language model adaptation using mixtures and an exponentially decaying cache," in Proc. ICASSP, 1997, pp. II:799-802.
12. S. Martin et al., "Adaptive topic-dependent language modeling using word-based varigrams," in Proc. Eurospeech, 1997, pp. 3:1447-1450.
13. D. Klakow, "Selecting articles from the language model training corpus," in Proc. ICASSP, 2000, pp. III:1695-1698.
14. A. Berger and R. Miller, "Just-in-time language modeling," in Proc. ICASSP, 1998, pp. II:705-708.
15. X. Zhu and R. Rosenfeld, "Improving trigram language modeling with the world wide web," in Proc. ICASSP, 2001, pp. I:533-536.
16. I. Bulyko, M. Ostendorf, and A. Stolcke, "Getting more mileage from web text sources for conversational speech language modeling using class-dependent mixtures," in P roc. HLT-NAACL, Comp. Vol., 2003, pp. 7-9.
17. R. Rosenfeld, "Optimizing lexical and n-gram coverage via judicious use of linguistic data," in Proc. Eurospeech, vol. 3,1995, pp. 1763-1766.
18. (1998) 1996 CSR Hub-4 Language Model. Linguistic Data Consortium. [Online], Available: http://morph.ldc.upenn.edu/Catalog/LDC98T31.html
19. R. Sproat, A. Black, S. Chen, S. Kumar, M. Ostendorf, and C. Richards, "Normalization of nonstandard words," Comput. Speech Lang., vol. 15, no. 3, pp. 287-333, July 2001.
20. S. Shwarm and M. Ostendorf, "Text normalization with varied data sources for conversational speech language modeling," in Proc. ICASSP, vol. I, 2002, pp. 789-792.
21. A. Ratnaparkhi, "A maximum entropy part-of-speech tagger," in Proc. Empirical Methods in Natural Language Processing Conference, 1996, pp. 133-141.
22. L. Bahl et al., "The IBM large vocabulary continuous speech recognition system for the ARPA NAB news task," in Proc. ARPA Workshop on Spoken Language Technology, 1995, pp. 121-126.
23. A. Stolcke, H. Bratt, J. Butzberger, H. Franco, V. R. R. Gadde, M. Plauche, C. Richey, E. Shriberg, K. Sommez, F. Weng, and J. Zheng, "The SRI March 2000 Hub-5 conversational speech transcription system," in Proc. NIST Speech Transcription Workshop, May 2000.
24. A. Stolcke, "SRILM - An extensible language modeling toolkit," in Proc. Intl. Conf. on Spoken Language Processing, vol. 2, 2002, pp. 901-904.
25. S. Chen and J. Goodman, "An empirical study of smoothing techniques for language modeling," Comput. Speech Lang., vol. 13, no. 4, pp. 359-394, 1999.
26. A. Stolcke, "Entropy-based pruning of backoff language models," in Proc. DARPA Broadcast News Transcription and Understanding Workshop, 1998, pp. 270-274.
27. N. Morgan, D. Baron, J. Edwards, D. Ellis, D. Gelbart, A. Janin, T. Pfau, E. Shriberg, and A. Stolcke, "The meeting project at ICSI," in Proc. Int. Conf. on Human Language Technology, 2001, pp. 246-252.
28. E. E. Shriberg, "To 'errrr' is human: Ecology and acoustics of speech disfluencies," J. Int. Phonetic Assoc., vol. 31, no. 1, pp. 153-169, 2001.
29. R. Iyer, M. Ostendorf, and M. Meteer, "Analyzing and predicting language model improvements," in Proc. IEEE Workshop on Speech Recognition and Understanding, 1997, pp. 254-261.
30. R. Iyer, "Improving and Predicting Performance of Statistical Language Models in Sparse Domains," Ph.D. dissertation, Boston Univ., Boston, MA, 1998.