On jointly learning the parameters in a character-synchronous integrated speech and language model

IEEE Transactions on Speech and Audio Processing

Volumn 4, Issue 3, 1996, Pages 167-189

  Chiang, Tung Hui ^a   Lin, Yi Chung ^b   Su, Keh Yih ^b  

^a INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE   (Taiwan)

^b NATIONAL TSING HUA UNIVERSITY   (Taiwan)

Author keywords

[No Author keywords available]

Indexed keywords

BIT ERROR RATE; MARKOV PROCESSES; MATHEMATICAL MODELS; MATHEMATICAL MORPHOLOGY; PERFORMANCE; SPEECH PROCESSING; SPEECH RECOGNITION;

HIDDEN MARKOV MODELS; JOINT LEARNING ALGORITHM; LANGUAGES PROCESSING; SPEECH MODULE; SPEECH RECOGNITION SYSTEM;

LEARNING ALGORITHMS;

EID: 0030143016     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.496214     Document Type: Article

References (44)

1. W. A. Lea, Ed., Trends in Speech Recognition. Englewood Cliffs, NJ: Prentice-Hall, 1980.
2. J. A. Barnett, M. I. Bernstein, and R. A. Gillmann, "The SDC speech understanding system," in Trends in Speech Recognition, W. A. Lea, Ed. Englewood Cliffs, NJ: Prentice-Hall, 1980, pp. 272-293.
3. D. E. Walker, "SRI research on speech understanding," in Trends in Speech Recognition, W. A. Lea, Ed. Englewood Cliffs, NJ: PrenticeHall, 1980, pp. 274-315.
4. F. L. Jelinek, R. Bahl, and R. L. Mercer, "Design of a linguistic statistical decoder for the recognition of continuous speech," IEEE Trans. Inform. Tlieory, vol. IT-21, no. 3, pp. 250-256, May 1975.
5. V. Digalakis and H. Murveit, "Genones: Optimizing the degree of mixture tying in a large vocabulary hidden Markov model based speech recognizer," in Proc. IEEE 1994 Int. Conf. Acoust., Speech, Signal Processing, Adelaide, Australia, Apr. 19-22, 1994, pp. 1537-540.
6. M. Hwang et al., "Improving speech recognition performance via phonedependent VQ codebooks and adaptive language models in SPHINX-II," in Proc. IEEE 1994 Int. Conf. Acoust., Speech, Signal Processing, Adelaide, Australia, Apr. 19-22, 1994, pp. 1549-1552.
7. J. L. Gauvain, L. F. Lamel, G. Adda, and M. Adda-Decker, "The LIMSI continuous speech dictation system: Evaluation on the APRA wall street journal task," in Proc. IEEE 1994 Int. Conf. Acoust., Speech, Signal Processing, Adelaide, Australia, pp. 1557-560.
8. P. C. Woodland, J. J. Odell, V. Valtchev, and S. J. Young, "Large vocabulary continuous speech recognition using HTK," in Proc. IEEE 1994 Int. Conf. Acoust., Speech, Signal Processing, Adelaide, Australia, 1994, pp. 11125-128.
9. X. Aubert, C. Dugast, H. Ney, and V. Steinbiss, "Large vocabulary continuous speech recognition of wall street journal data," in Proc. IEEE 1994 Int. Conf. Acoust., Speech, Signal Processing, Adelaide, Australia, pp. 11129-132.
10. L. R. Bahl et al., "Performance of the IBM large vocabulary continuous speech recognition system on the ARPA Wall Street Journal task," in Proc. IEEE 1995 Int. Conf. Acoust., Speech, Signal Processing, Detroit, MI, USA, May 1995, pp. 41-14.
11. B. P. Douglas, "New developments in the Lincoln stack-decoder based large-vocabulary CSR system," in Proc. IEEE 1995 Int. Conf. Acoust., Speech, Signal Processing, Detroit, MI, May 1995, pp. 45-48.
12. T. Robinson et al, "WSJCAMO: A British English speech corpus for large vocabulary continuous speech recognition," in Proc. IEEE 1995 Int. Conf. Acoust., Speech, Signal Processing, Detroit, MI, May 1995, pp. 81-84.
13. K. Y. Su, T. H. Chiang, and Y. C. Lin, "A unified probabilistic score function for integrating speech and language information in spoken language processing," in Proc. 7990 Int. Conf. Spoken Language Processing, Kobe, Japan, Nov. 1990, pp. 901-904.
14. _, "A unified framework to incorporate speech and language information in spoken language processing," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, ICASSP-92, San Francisco, CA, Mar. 1992, pp. 1185-188.
15. P. F. Brown, "Classed-based ?i-gram models of natural language," Computat. Linguist., vol. 18, no. 4, pp. 467-479, 1992.
16. L. S. Lee et al., "System description of the golden mandarin (I) voice input system for unlimited Chinese character," in Proc. /99/ Int. Conf. Comput. Processing Chinese Orient. Lang., Taipei, Taiwan, Aug. 1991, pp. 45-50.
17. _, "Golden mandarin (I)-A real-time mandarin speech dictation machine for Chinese language with very large vocabulary," IEEE Trans. Speech Audio Processing, vol. 1, no. 2, pp. 158-179, Apr. 1993.
18. _, "Golden mandarin (II)-An improved single-chip real-time mandarin dictation machine for Chinese language with very large vocabulary," in Proc. IEEE 1993 Int. Conf. Acoust., Speech, Signal Processing, Apr. 1993, pp. 11503-506.
19. ne BDC Chinese-English Electronic Dictionary: Version 2. Behavior Design Corporation, 1993.
20. S. Katagiri, C. H. Lee, and B. H. Juang, "New discriminative training algorithm based on the generalized probabilistic decent method," in Proc. 1991 IEEE Workshop Neural Nertvorks Signal Processing, Piscataway, NJ, Aug. 1991, pp. 299-308.
21. K. Y. Su and C. H. Lee, "Robustness and discrimination oriented speech recognition using weighted HMM and subspace projection approaches," in Proc. IEEE 1991 Int. Conf. Acoust., Speech, Signal Processing, Toronto, Canada, May 1991, pp. 541-544.
22. _, "Speech recognition using weighted HMM and subspace projection approaches," IEEE Trans. Speech Audio Processing, vol. 2, no. 1, pp. 69-79, Jan. 1994.
23. B. H. Juang, and S. Katagiri, "Discriminative learning for minimum error classification," IEEE Trans. Acoust., Speech, Signal Processing, vol. 40, no. 12, pp. 3043-3054, Dec. 1992.
24. X. Huang, M. Belin, F. Alleva, and M. Hwang, "Unified stochastic engine (USE) for speech recognition," in Proc. IEEE 1993 Int. Conf. Acoust., Speech, Signal Processing, Apr. 1993, pp. 11636-639.
25. D. W. Massaro, M. M. Cohen, and C. Y. Tseng, "The evaluation and integration of pitch height and pitch contour in lexical tone perception in mandarin Chinese," J. Chinese Linguist., vol. 12, no. 2, 1980.
26. L. R. Rabiner, J. G. Wilpon, and B. H. Juang, "A segmental fc-means training procedure for connected word recognition," AT&T Tech. J, vol. 65, no. 3, pp. 21-31, May-June 1986.
27. L. R. Rabiner, "A tutorial on hidden Markov models and selected applications in speech recognition," Proc. IEEE, vol. 77, no. 2, pp. 1404-1413, Feb. 1989.
28. J. S. Chang, C. D. Chen, and S. D. Chen, "Chinese word segmentation through constraint satisfaction and statistical optimization," in'Proc. ROCL1NG-1V, ROC Computat. Linguist. Conf., Renting, Taiwan, ROC, 1991, pp. 147-165.
29. T. H. Chiang, M. Y. Lin, and K. Y. Su, "Statistical models for word segmentation and unknown word resolution," in Proc. 1992 R.O.C. Computat. Linguist. Conf. (ROCLING V), Taipei, Taiwan, 1992, pp. 121-146.
30. H. J. Chen and S. H. Liu, "Word identification for mandarin Chinese sentences," in Proc. COLING-92, 14lh Int. Conf. Computat. Linguist., Nantes, France, July 1992, pp. 101-107.
31. R. Garside, G. Leech, and G. Sampson, Tlie Computational Analysis of English: A Corpus-Based Approach. London: Longman.
32. K. Church, "A stochastic parts program and noun phrase for unrestricted text," in ACL Proc. 2nd Conf. Appl. Natural Lang. Processing, Austin, TX, Feb. 1988, pp. 136-143.
33. B. Merialdo, 'Tagging text with a probabilistic model," in Proc. IEEE 1991 Int. Conf. Acoust., Speech, Signal Processing, Toronto, Canada, May 1991, pp. 809-812.
34. S. C. Chen, J. S. Chang, J. N. Wang, and K. Y. Su, "ArchTran: A corpusbased statistics-oriented English-Chinese machine translation system," in Proc. Machine Translat. Summit III, Washington, DC, USA, July 1991.
35. K. Y. Su, J. N. Wang, M. H. Su, and J. S. Chang, "GLR parsing with scoring," in Generalized LR Parsing, T. Masaru, Ed. Boston, MA: Kluwer, 1991, pp. 93-112.
36. T. H. Chiang, Y. C. Lin, and K. Y. Su, "Syntactic ambiguity resolution using a discrimination and robustness oriented adaptive learning algorithm," in Proc. COLING-92, 14th Int. Conf. Computat. Linguist. Nantes, France, July 1992, pp. 352-358.
37. K. Y. Su, J. S. Chang, Y. C. Lin, and T. H. Chiang, "A unified approach to disambiguation using a uniform formulation of probabilistic score function," in preparation.
38. L. R. Bah!, F. Jelinek, and R. Mercer, "A maximum likelihood approach to continuous speech recognition," IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-5, no. 2, pp. 179-190, Mar. 1983.
39. K. F. Lee, H. W. Hon, and R. Reddy, "An overview of the sphinx speech recognition system," IEEE Trans. Acoust., Speech, Signal Processing, vol. 38, no. 1, pp. 35-45, Jan. 1990.
40. R. Schwanz et ai., "Context-dependent modeling for acoustic-phonetic recognition of continuous speech," in Proc. IEEE 1985 Int. Conf. Acoust., Speech, Signal Processing, 1985, pp. 1205-1208.
41. H. Key, R. Haeb-Umback, B. H. Tran, and M. Oerder, "Improvements in beam search for 1000-word continuous speech recognition," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Processing, ICASSP-92, San Francisco, CA, Mar. 1992, pp. 19-12.
42. M. Phillips and D. Goddeau, "Fast match for segment-based largevocabulary continuous speech recognition," in Proc. 1994 Int. Conf. Spoken Lang. Processing, Yokohama, Japan, Sept. 1994, pp. 1359-1362.
43. V. Valtchev, J. J. Odell, P. C. Woodland, and S. J., Young,."A dynamic network decoder design for large vocabulary speech recognition," in Proc. 1994 Int. Conf. Spoken Lang. Processing, Yokohama, Japan, Sept. 1994, pp. 1351-1354.
44. S. Amari, "A theory of adaptive pattern classifiers," IEEE Trans. Electron. Comput., vol. EC-16, pp. 299-307, June 1967.