Modeling long distance dependence in language: Topic mixtures versus dynamic cache models

IEEE Transactions on Speech and Audio Processing

Volumn 7, Issue 1, 1999, Pages 30-39

  Iyer, Rukmini M ^a   Ostendorf, Mari ^a  

^a Boston University   (United States)

Author keywords

Cache language model; Ii gram; Mixture language model; Topic dependent language model

Indexed keywords

MATHEMATICAL MODELS; STATISTICAL METHODS;

CACHE LANGUAGE MODEL;

SPEECH PROCESSING;

EID: 0032785782     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.736328     Document Type: Article

References (33)

1. F. Jelinek, R. L. Mercer, and S. Roukos, "Principles of lexical language modeling for speech recognition," in Readings in Speech Recognition, A. Waibel and K.-F. Lee, Eds. San Mateo, CA: Morgan Kaufmann, 1990, pp. 651-699.
2. 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.
3. R. Kühn and R. de Mon, "A cache based natural language model for speech recognition," IEEE Trans. Pattern Anal. Machine Intell., vol. 14, pp. 570-583, 1992.
4. R. Rosenfeld, "A hybrid approach to adaptive statistical language modeling," in Proc. ARPA Workshop on Human Language Technology, 1994, pp. 76-87.
5. J. H. Wright, G. J. F. Jones, and E. N. Wrigley, "Hybrid grammar bigram speech recognizer system with first-order dependence model," in Proc. Int. Conf. Acoustics, Speech, and Signal Proc., 1992, vol. I, pp. 169-171.
6. F. Jelinek, J. Lafferty, and R. Mercer, "Basic methods of probabilistic context-free grammars," in Speech Recognition and Understanding: Recent Advances, Trends, and Applications, Series F: Computer and Systems Sciences, P. Laface and R. De Mon, Eds. Berlin, Germany: Springer-Verlag, 1992, vol. 75.
7. M. Meteer and J. R. Rohlicek, "Statistical language modeling combining Ar-gram and context free grammars," in Proc. Int. Conf. Acoustics, Speech, Signal Processing, 1993, vol. II, pp. 37-40.
8. R. Lau, R. Rosenfeld, and S. Roukos, 'Trigger-based language models: A maximum entropy approach," in Proc. Int. Conf. Acoustics, Speech, Signal Processing, 1993, vol. II, pp. 45-48.
9. L. R. Bahl, P. F. Brown, P. V. deSouza, and R. L. Mercer, "A tree-based statistical language model for natural language speech recogration," IEEE Trans. Acoustics, Speech, Signal Processing, vol. 37, pp. 1001-1008, 1989.
10. R. lyer, M. Ostendorf, and R. Rohlicek, "An improved language model using a mixture of Markov components," in Proc. ARPA Workshop on Human Language Technology, 1994, pp. 82-87.
11. M. Ostendorf et al., "Integration of diverse recognition methodologies through réévaluation of jY-best sentence hypotheses," in Proc. ARPA Workshop on Speech and Natural Language, 1991, pp. 83-87.
12. R. Kneser and V. Steinbiss, "On the dynamic adaptation of stochastic LM," in Proc. Int. Conf. Acoustics, Speech, Signal Processing, 1993, vol. 2, pp. 586-589.
13. L. Bahl et al., "The IBM large vocabulary continuous speech recognition system for the ARPA NAB news task," in P roc. ARPA Workshop on Spoken Language Technology, 1995, pp. 121-126.
14. F. Kubala, "Design of the 1994 CSR benchmark tests," in Proc. ARPA Workshop on Spoken Language Technology, 1995, pp. 41-46.
15. J. J. Godfrey, E. C. Holliman, and J. McDaniel, "Switchboard: Telephone speech corpus for research and development," in Proc. Int. Conf. Acoustics, Speech, Signal Processing, 1992, vol. 1, pp. 517-520.
16. S. Sekine, "Automatic sublanguage identification for a new text," in 2nd Ann. Workshop on Very Large Corpora, Kyoto, Japan, 1994, pp. 109-120.
17. R. O. Duda and P. E. Hart, Pattern Classification and Scene Analysis. New York: Wiley, 1973.
18. A. Dempster, N. Laird, and D. Rubin, "Maximum likelihood from incomplete data via the EM algorithm," J. R. Stat. Soc. B, vol. 39, pp. 1-22, 1977.
19. L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," Proc. IEEE, vol. 77, pp. 257-285, 1989.
20. P. Placeway, R. Schwanz, P. Fung, and L. Nguyen, "Estimation of powerful LM from small and large corpora," in Proc. Int. Conf. Acoustics, Speech, and Signal Processing, vol. 2, pp. 33-36, 1993.
21. Y. Linde, A. Buzo, and R. M. Gray, "An algorithm for vector quantizer design," IEEE Trans. Commun., vol. COMM-28, pp. 84-95, 1980.
22. W. Byrne, "Encoding and representing phonemic sequences using nonlinear networks," Ph.D. dissertation, Univ. Maryland, College Park, 1993.
23. R. lyer, "Language modeling with sentence-level mixtures," M.S. thesis, Boston Univ., Boston, MA, 1994.
24. M. Ostendorf et al., "The 1994 BU NAB news benchmark system," in Proc. ARPA Workshop on Spoken Language Technology, 1995, pp. 139-142.
25. M. Ostendorf, V. Digalakis, and O. Kimball, "From HMM's to segment models: A unified view of stochastic modeling for speech recognition," IEEE Trans. Speech Audio Processing, vol. 4, pp. 360-378, 1996.
26. L. Nguyen etal., "The 1994 BBN/BYBLOS speech recognition system," in Proc. ARPA Workshop on Spoken Language Technology, 1995, pp. 77-81.
27. A. Kannan, M. Ostendorf, and J. R. Rohlicek, "Weight estimation for jY-best rescoring," in Proc. ARPA Workshop on Speech and Natural Language, 1992, pp. 455-456.
28. E-mail: ldc@unagi.cis.upenn.edu.
29. R. Rosenfeld, "The CMU statistical language modeling toolkit and its use in the 1994 ARPA CSR evaluation," in Proc. ARPA Workshop on Spoken Language Technology, 1995, pp. 47-50.
30. D. Pallet! et al, "I994 benchmark tests for the ARPA spoken language program," in Proc. ARPA Workshop on Spoken Language Technology, 1995, pp. 5-36.
31. D. Dahl et al, "Expanding the dcope of the ATIS task: The ATIS-3 corpus," in Proc. ARPA Workshop on Human Language Technology, 1994, pp. 43-48.
32. R. lyer, M. Ostendorf, and H. Gish, "Using out-of-domain data to improve in-domain language models," IEEE Signal Processing Lett., vol. 4, pp. 221-223, 1997.
33. R. lyer and M. Ostendorf, 'Transforming out-of-domain estimates to improve in-domain language models," in Proc. Europ. Conf. Speech Communication and Technology, 1997, vol. 4, pp. 1975-1978.