Modeling linguistic features in speech recognition

EUROSPEECH 2003 - 8th European Conference on Speech Communication and Technology

Volumn , Issue , 2003, Pages 2585-2588

  Tang, Min ^a   Seneff, Stephanie ^a   Zue, Victor W ^a  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

LINGUISTICS; SPEECH; SPEECH COMMUNICATION;

COMPUTATION TIME; DETAILED MODELS; ISOLATED WORDS; LINGUISTIC FEATURES; NEW APPROACHES; PERFORMANCE GAIN; SUB-WORD UNITS; TELEPHONE SPEECH RECOGNITION;

SPEECH RECOGNITION;

EID: 85009204121     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (20)

1. Y. Chow, M. Dunham, O. Kimball, M. Krasner, G. F. Kubula, J. Markhoul, P. Price, S. Roucos, and R. Schwartz, "BYBLOS: The BBN continuous speech recognition system," in Proc. IEEE Int. Conf. ASSP, 1987, pp. 89-92.
2. K.-F. Lee, Automatic Speech Recognition: The Development of the SPHINX System. Boston: Kluwer Academic Publishers, 1989.
3. S. J. Young, J. J. Odell, and P. C.Woodland, "Tree-based state typing for high accuracy acoustic modelling," in Proceedings ARPA Workshop on Human Language Technology, 1994, pp. 307-312.
4. C. Wang, S. Cyphers, X. Mou, J. Ponifroni, S. Seneff, J. Yi, and V. Zue, "Muxing: A telephone-access Mandarin conversational system," in Proc. ICSLP, Beijing, P.R.China, October 2000.
5. K. N. Stevens, Acoustic Phonetics. MIT Press, 1998.
6. K. Kirchhoff, "Robust speech recognition using articulatory information," Ph.D. dissertation, Der Technischen Fakult?at der Universit ?at Bielefeld, 1999.
7. M. Richardson, J. Bilmes, and C. Diorio, "Hidden-articulator Markov models: Performance improvements and robustness to noice," in Proc. ICSLP, 2000.
8. E. Eide, "Distinctive features for use in an automatic speech recognition system," in Proc. Eurospeech, 2001.
9. J. Sun and L. Deng, "An overlapping-feature-based phonological model incorporating linguistic constraints: Application to speech recognition," Journal of Acoustic Society American, vol. 111, no. 2, Feburary 2002.
10. D. P. Huttenlocher and V.W. Zue, "A model of lexical access from partial phonetic information," in Proc. IEEE Int. Conf. ASSP, San Diego, CA, March 1984.
11. J. A. Goldsmith, Autosegmental and Metrical Phonology. Basil Blackwell, 1989.
12. K. N. Stevens, "Toward a model for lexical access based on acoustic landmarks and distinctive features," Journal of Acoustic Society American, vol. 111, no. 4, pp. 1872-1891, April 2002.
13. E. C. Sagey, "The representation of features and relations in nonlinear phonolgy," Ph.D. dissertation, Massachusetts Institute of Technology, 1982.
14. J. Glass, "A probabilistic framework for segment-based speech recognition," Computer Speech and Language, p. To Appear, 2003.
15. J. Fiscus, "A post-processing system to yield reduced word error rates: Recognizer output voting error reduction (ROVER)," in Proc. of IEEE Workshop on Automatic Speech Recognition and Understanding, Santa Barbara, California, 1997.
16. K. Livescu and J. R. Glass, "Segment-based recognition on the Phonebook task: Initial results and observations on duration modeling," in Proc. Eurospeech, 2001.
17. J. Pitrelli, C. Fong, S.Wong, J. Splitz, and H. Leung, "Phonebook: A phonetically-rich isolated-word telephone-speech database," in Proc. IEEE Int. Conf. ASSP, 1995, pp. 101-104.
18. S. Dupont, H. Bourlard, O. Deroo, V. Fontaine, and J. M. Boite, "Hybrid HMM/ANN systems for training independent tasks: Experiments on Phonebook and related improvements," in Proc. IEEE Int. Conf. ASSP, 1997.
19. J.A.Bilmes, "Dynamic Bayesian multinets," in Proc. 16 Conf. on Uncertainty in Artificial Intelligence, 2000.
20. S. Seneff, "The use of linguistic hierarchies in speech understanding," in Proc. ICSLP, 1998.