Pronunciation modeling using a finite-state transducer representation

Speech Communication

Volumn 46, Issue 2, 2005, Pages 189-203

  Hazen, Timothy J ^a   Hetherington, I Lee ^a   Shu, Han ^a   Livescu, Karen ^a  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; FINITE AUTOMATA; INFORMATION ANALYSIS; LINGUISTICS; MATHEMATICAL MODELS; PROBLEM SOLVING;

FINITE STATE TRANSDUCERS (FST); INFORMATION SYSTEMS; PHONOLOGY; TRANSITION WEIGHT;

SPEECH RECOGNITION;

EID: 19944423811     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2005.03.004     Document Type: Conference Paper

References (25)

1. Church, K., 1983. Phrase structure parsing: A method for taking advantage of allophonic constraints. Ph.D. thesis, Massachusetts Institute of Technology, Cambridge, MA.
2. A. Dempster, N. Laird, and D. Rubin Maximum likelihood from incomplete data via the EM algorithm J. Roy. Statist. Soc. Ser. B 39 June 1977 1 38
3. Eisner, J., 2002. Parameter estimation for probabilistic finite-state transducers. In: Proc. Annual Meeting of the Association for Computational Linguistics, Philadelphia, Pennsylvania. ACL, East Stroudsburg, Pennsylvania, pp. 1-8.
4. Gillick, L., Cox, S., 1989. Some statistical issues in the comparison of speech recognition algorithms. In: Proc. 1989 IEEE International Conference on Acoustics, Speech, and Signal Processing, Glasgow, Scotland. IEEE, Piscataway, New Jersey, pp. 532-535.
5. J. Glass A probabilistic framework for segment-based speech recognition Computer Speech Language 17 2-3 2003 137 152
6. Glass, J., Hazen, T.J., Hetherington, I.L., 1999. Real-time telephone-based speech recognition in the jupiter domain. In: Proc. 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing, Phoenix, Arizona. IEEE, Piscataway, New Jersey, pp. 61-64.
7. S. Greenberg Speaking in shorthand-A syllable-centric perspective for understanding pronunciation variation Speech Comm. 29 2-4 1999 159 176
8. Hain, T., 2002. Implicit pronunciation modelling in ASR. In: Proc. ISCA Tutorial and Research Workshop on Pronunciation Modeling and Lexicon Adaptation for Spoken Language, Estes Park, Colorado. ISCA, Bonn, pp. 129-134.
9. Hazen, T.J., Hetherington, L.I., Shu, H., Livescu, K., 2002. Pronunciation modeling using a finite-state transducer representation. In: Proc. ISCA Tutorial and Research Workshop on Pronunciation Modeling and Lexicon Adaptation for Spoken Language, Estes Park, Colorado. ISCA, Bonn, pp. 99-104.
10. Hetherington, L.I., 2001. An efficient implementation of phonological rules using finite-state transducers. In: Proc. 7th European Conference on Speech Communication and Technology (EUROSPEECH), Aalborg, Denmark. Kommunik Grafiske Løsniger A/S, Aalborg, pp. 1599-1602.
11. Jurafsky, D., et al., 2001. What kind of pronunciation variation is hard for triphones to model? In: Proc. 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing, Salt Lake City, Utah. IEEE, Piscataway, New Jersey, pp. 577-580.
12. Lamel, L., Adda, G., 1996. On designing pronunciation lexicons for large vocabulary, continuous speech recognition. In: Proc. Fourth International Conference on Spoken Language Processing, Philadelphia, Pennsylvania. Citation Delaware, New Castle, Delaware, pp. 6-9.
13. Livescu, K., Glass, J., 2000. Lexical modeling of non-native speech for automatic speech recognition. In: Proc. 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing, Istanbul, Turkey. IEEE, Piscataway, New Jersey, pp. 1842-1845.
14. McAllaster, D., Gillick, L., Scattone, F., Newman, M., 1998. Fabricating conversational speech data with acoustic models: A program to examine model-data mismatch. In: Proc. 5th International Conference on Spoken Language Processing, Sydney, Australia. Causal Productions Pty Ltd., Adelaide, Australia, pp. 1847-1850.
15. F. Pereira, and M. Riley Speech recognition by composition of weighted finite automata E. Roche Y. Schabes Finite-state language processing 1997 MIT Press Cambridge, MA 431 453
16. M. Riley Stochastic pronunciation modelling from hand-labelled phonetic corpora Speech Comm. 29 2-4 1999 209 224
17. S. Seneff The use of subword linguistic modelling for multiple tasks in speech recognition Speech Comm. 42 April 2004 373 390
18. Seneff, S., Wang, C., 2002. Modelling phonological rules through linguistic hierarchies. In: Proc. ISCA Tutorial and Research Workshop on Pronunciation Modeling and Lexicon Adaptation for Spoken Language, Estes Park, Colorado. ISCA, Bonn, pp. 71-76.
19. Shafran, I., 2001. Clustering wide contexts and HMM topologies for spontaneous speech recognition. Ph.D. thesis, University of Washington, Seattle, Washington, 2001.
20. Shu, H., Hetherington, L.I., 2002. EM training of finite-state transducers and its application to pronunciation modeling. In: Proc. 7th International Conference on Spoken Language Processing, Denver, Colorado. Causal Productions Pty Ltd., Adelaide, Australia, pp. 1293-1296.
21. Ström, N., Hetherington, L.I., Hazen, J.T., Sandness, E., Glass, J., 1999. Acoustic modeling improvements in a segment-based speech recognizer. In: Proc. IEEE 1999 Automatic Speech Recognition and Understanding Workshop, Keystone, Colorado. IEEE, Piscataway, New Jersey, pp. 139-142.
22. Tajchman, G., Fosler, E., Jurafsky, D., 1995. Building multiple pronunciation models for novel words using exploratory computational phonology. In: Proc. 4th European Conference on Speech Communication and Technology (EUROSPEECH), Madrid, Spain. Gráficas Brens, Madrid, pp. 2247-2250.
23. Yi, J., Glass, J., 2002. Information-theoretic criteria for unit selection synthesis. In: Proc. 7th International Conference on Spoken Language Processing, Denver, Colorado. Causal Productions Pty Ltd., Adelaide, Australia, pp. 2617-2620.
24. Yi, J., Glass, J., Hetherington, L., 2000. A flexible, scalable finite-state transducer architecture for corpus-based concatenative speech synthesis. In: Proc. 6th International Conference on Spoken Language Processing, Beijing, China. China Military Friendship Publishers, Beijing, pp. 322-325.
25. V. Zue Jupiter: A telephone-based conversational interface for weather information IEEE Trans. Speech Audio Process. 8 1 2000 85 96