The use of subword linguistic modeling for multiple tasks in speech recognition

Speech Communication

Volumn 42, Issue 3-4, 2004, Pages 373-390

  Seneff, Stephanie ^a  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

CODES (SYMBOLS); DATA ACQUISITION; LINGUISTICS; PROJECT MANAGEMENT; RESEARCH; SOCIETIES AND INSTITUTIONS; STUDENTS;

AUTOMATIC ACQUISITION; HUMAN COMMUNICATION;

SPEECH RECOGNITION;

EID: 1842527766     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2003.11.001     Document Type: Article

References (51)

1. Allen, J., Hunnicutt, M.S., Klatt, D., 1987. From Text to Speech: The MITalk System. Cambridge Studies in Speech and Science Communication. Cambridge University Press, Cambridge.
2. Bacchiani, M., Ostendorf, M., 1998. Using automatically derived acoustic subword units in large vocabulary speech recognition. In: Proc. ICSLP'98, Vol. IV, Sydney, Australia, November 1998, pp. 1319-1322.
3. Bazzi, I., Glass, J., 2001. Learning units for domain-independent out-of-vocabulary word modeling. In: Proc. Eurospeech, Aalborg, Denmark, pp. 61-64.
4. Chomsky, N., Halle, M., 1968. The Sound Pattern of English. Harper & Row, New York, NY (Republished in Paperback, MIT Press, Cambridge, MA, 1991).
5. Chung, G., 1997. Hierarchical Duration Modeling for a Speech Recognition System. S.M. Thesis, MIT Department of Electrical Engineering and Computer Science.
6. Chung, G., 2000a. Automatically incorporating unknown words in Jupiter. In: Proc. ICSLP, Beijing, China, October 2000, pp. 520-523.
7. Chung, G., 2000b. A three-stage solution for flexible vocablary speech understanding. In: Proc. ICSLP 2000, Beijing, China, October 2000, pp. 266-269.
8. Chung, G., 2001. Towards multi-domain speech understanding with flexible and dynamic vocabulary. Ph.D. Dissertation, MIT Department of Electrical Engineering and Computer Science, June 2001.
9. Chung, G., Seneff, S., 1997. Hierarchical duration modeling for speech recognition using the ANGIE framework. In: Proc. EUROSPEECH'97, Rhodes, Greece, September 1997, pp. 1475-1478.
10. Chung, G., Seneff, S., 1998. Improvements in speech understanding accuracy through the integration of hierarchical linguistic, prosodic, and phonological constraints in the Jupiter domain. In: ICSLP'98, Sydney, Australia, December 1998, pp. 935-939.
11. Chung, G., Seneff, S., 2002. Integrating speech with keypad input for automatic entry of spelling and pronunciation of new words. In: Proc. ICSLP '02, Vol. III, Denver, CO, September 2002, pp. 2061-2064.
12. Chung, G., Seneff, S., Wang, C., 2003. Automatic acquisition of names using speak and spell mode in spoken dialogue systems. In: Proc. HLT-NAACL, Edmonton, Canada, May 2003, pp. 32-39.
13. Church, K.W., 1983. Phrase-structure parsing: a method for taking advantage of allophonic constraints. Ph.D. Thesis, Department of Electrical Engineering and Computer Science, MIT, Cambridge, MA.
14. Cohen, M.H., 1989. Phonological structures for speech recognition. Ph.D. Dissertation, University of California, Berkeley, CA.
15. Cole, R. et al., 1992. A telephone speech database of spelled and spoken names. In: Proc. ICSLP'92, Banff, Canada, October 1992.
16. Cook, G., Robinson, T., Christie, J., 1998. Real-time recognition of broadcast news. In: Proc. ICSLP'98, Vol. IV, Sydney, Australia, November 1998, pp. 1319-1322.
17. Dupont, S., Bourlard, H., Deroo, O., Fontaine, V., Boite, J.-M., 1990. Hybrid HMM/ANN systems for training independent tasks: experiments on phonebook and related improvements. In: Proc. ICASSP, Albuquerque, NM.
18. Gabovich, V.Y., 2002. A multi-stage sound-to-letter recognizer. M.Eng Thesis, MIT, May 2002.
19. Gauvain, J.L., Lamel, L.F., Adda, G., Adda-Decker, M., 1993. Speaker independent continuous speech dictation. In: Proc. EUROSPEECH'93, Berlin, Germany, September 1993, pp. 125-128.
20. Glass, J., Chang, J., McCandless, M., 1996. A probabilistic framework for feature-based speech recognition. In: Proc. ICSLP'96, Philadelphia, PA, October 1996, pp. 2277-2280.
21. Glass, J.R., Hazen, T.J., Telephone-based conversational speech recognition in the Jupiter domain. In: ICSLP'98, Sydney, Australia, December 1998, pp. 1327-1330.
22. Godfrey, J., Holliman, E., McDaniel, J., 1992. SWITCHBOARD: telephone speech corpus for research and development. In: Proc. ICASSP-92, San Francisco, pp. 517-520.
23. Greenberg S. Speaking in shorthand - a syllable-centric perspective for understanding pronunciation variation. Speech Commun. 29:1999;159-176.
24. Hayes B. Metrical Stress Theory: Principles and Case Studies. 1995;University of Chicago Press, Chicago.
25. Hetherington, I.L., 1994. The problem of new, out-of-vocabulary words in spoken language systems. Ph.D. Thesis, Department of Electrical Engineering and Computer Science, MIT, Cambridge, MA, October 1994.
26. Hetherington, I.L., 2001. An efficient implementation of phonological rules using finite state transducers. In: Proc. Eurospeech 2001, Aalborg, Denmark, September 2001, pp. 1599-1602.
27. Hetherington, I.L., Zue, V., 1993. New words: implications for continuous speech recognition. In: Proc. Third European Conf. on Speech Communication and Technology, Berlin, Germany, September 1993.
28. Kahn, D., 1976. Syllable-based generalizations in English phonology. Ph.D. Thesis, Department of Linguistics and Philosophy, MIT, Cambridge, MA.
29. Kucera H., Francis W. Computational Analysis of Present-Day American English. 1967;Brown University Press.
30. Lau, R., 1998. Subword lexical modeling for speech recognition. Ph.D. Thesis, Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, May 1998.
31. Lau, R., Seneff, S., 1997. Providing sublexical constraints for word spotting within the ANGIE framework. In: Proc. EUROSPEECH'97, Rhodes, Greece, September 22-25, 1997, pp. 263-266.
32. Lau, R., Seneff, S., 1998. A unified system for sublexical and linguistic modeling using ANGIE and TINA. In: ICSLP'98, Sydney, Australia, December 1998, pp. 2443-2446.
33. Meng, H., 1995. Phonological parsing for bi-directional letter-to-sound/sound-to-letter generation. Ph.D. Thesis, Department of Electrical Engineering and Computer Science, MIT, Cambridge, MA, June 1995.
34. Meng H., Hunnicutt S., Seneff S., Zue V. Reversible letter-to-sound/ sound-to-letter generation based on parsing word morphology. Speech Commun. 18:1996;47-63.
35. Mou, X., Seneff, S., Zue, V., 2001. Context-dependent probabilistic hierarchical sub-lexical modeling using finite state transducers. In: Proc. EUROSPEECH 2001, Aalborg, Denmark, September 2001, pp. 451-454.
36. Nguyen, L., Anastasakos, T., Kubala, F., LaPre, C., Makhoul, J., Schwartz, R., Yuan, N., Zavaliagkos, G., Zhao, Y., 1995. The 1994 BBN/BYBLOS speech recognition system. In: Proc. ARPA Spoken Language Systems Technology Workshop'95, Austin, TX, January 1995, pp. 693-696.
37. Onishi, S., Yamamoto, H., Sagisaka, Y., 2001. Structured language model for class identification of out-of-vocabulary words arising from multiple word classes. In: EUROSPEECH 2001, AAlborg, Denmark, September 2001, pp. 693-696.
38. Parmar, A.D., 1997. A semi-automatic system for the syllabification and stress assignment of large lexicons. M.Eng Thesis, Department of Electrical Engineering and Computer Science, MIT, Cambridge, MA, June 1997.
39. Randolph, M.A., 1989. Syllable-based constraints on properties of English sounds. Ph.D. Thesis, Department of Electrical Engineering and Computer Science, MIT, Cambridge, MA, September 1989.
40. Scalise S. Generative Morphology. 1986;Foris Publications, Dordrecht, Netherlands.
41. Seneff S. TINA: a natural language system for spoken language applications. Comput. Linguist. 18(1):1992;61-86.
42. Seneff, S., 1998. The use of linguistic hierarchies in speech understanding. Keynote Address. In: ICSLP'98, Sydney, Australia, December 1998, pp. 3321-3330.
43. Seneff, S., Polifroni, J., 2000. Dialogue management in the mercury flight reservation system. In: Proc. ANLP-NAACL 2000, Satellite Workshop, Seattle, Washington, May 2000, pp. 1-6.
44. Seneff, S., Wang, C., 2002. Modelling phonological rules through corpus-trained linguistic hierarchies. In: ISCA Tutorial and Research Workshop on Pronunciation Modeling and Lexicon Adaptation for Spoken Language, Estes Park, CO, September 2002, pp. 71-76.
45. Seneff, S., Lau, R., Meng, H., 1996. ANGIE: A new framework for speech analysis based on morpho-phonological modeling. In: Proc. ICSLP'96, Vol. 1, Philadelphia, PA, October 1996, pp. 110-113. Available from < http://www.sls.lcs.mit.edu/raylau/icslp96_angie.pdf >.
46. Seneff, S., Chuu, C., Cyphers, D.S., 2000. ORION: from on-line interaction to off-line delegation. In: Proc. ICSLP '00, Vol. II, Beijing, China, October 2000, pp. 142-145.
47. Selkirk E. Syllables. van der Hulst Harry, Smith Norval The Structure of Phonological Representations. 1982;337-383 Foris, Dordrecht.
48. Weintraub, M., Murveit, H., Cohen, M., Price, P., Bernstein, J., Baldwin, G., Bell, D., 1989. Linguistic constraints in hidden Markov model based speech recognition. In: Proc. ICASSP '89, Glasgow, Scotland, May 1989, pp. 699-702.
49. Woodland, P.C., Young, S.J., 1993. The HTK tied-state continuous speech recognizer. In: Proc. European Conf. on Speech Commun. and Technology, Vol. 3, pp. 2207-2210.
50. Zue V. The use of Phonetic rules in automatic speech recognition. Speech Commun. 2:1983;181-186.
51. Zue, V., Glass, J., Goodine, D., Hirschman, L., Leung, H., Phillips, M., Polifroni, J., Seneff, S., 1991. The MIT ATIS system: preliminary development, spontaneous speech data collection and performance evaluation. In: Proc. European Conf. on Speech Communication and Technology, Vol. 2, Genoa, Italy, September 1991, pp. 537-541.