A probabilistic framework for segment-based speech recognition

Computer Speech and Language

Volumn 17, Issue 2-3, 2003, Pages 137-152

  Glass, James R ^a  

^a MASSACHUSETTS INSTITUTE OF TECHNOLOGY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER SIMULATION; DECODING; FEATURE EXTRACTION; GRAPH THEORY; MATRIX ALGEBRA; MAXIMUM LIKELIHOOD ESTIMATION; RANDOM PROCESSES; SPEECH ANALYSIS; VECTORS; WORD PROCESSING;

ACOUSTIC LIKELIHOOD ESTIMATION; SEGMENT BASED SPEECH RECOGNITION; WORD RECOGNITION;

SPEECH RECOGNITION;

EID: 0038359548     PISSN: 08852308     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0885-2308(03)00006-8     Document Type: Article

References (43)

1. Chang, J., 1998. Near-miss modeling: a segment-based approach to speech recognition. Ph.D. thesis, EECS, MIT.
2. Chang, J., Glass, J., 1997. Segmentation and modeling in segment-based recognition. In: Proc. Eurospeech, Rhodes, Greece, October, pp. 1199-1202.
3. Cohen, J., 1981. Segmenting speech using dynamic programming. J. Acoust. Soc. Am. 69 (5), 1430-1438.
4. Cole, R., Stern, R., Phillips, M., Brill, S., Pilant, A., Specker, P., 1983. Feature-based speaker-independent recognition of isolated letters. In: Proc. ICASSP, Boston, MA, pp. 731-733.
5. Digilakis, V., 1992. Segment-based stochastic models of spectral dynamics for continuous speech recognition. Ph.D. thesis, Boston University.
6. Digilakis, V., Rohlicek, J., Ostendorf, M., 1993. ML estimation of a stochastic linear system with the EM algorithm and its application to speech recognition. IEEE Trans. Speech Audio Proc. 1 (4), 431-442.
7. Garofolo, J., Lamel, L., Fisher, W., Fiscus, J., Pallet, D., Dahlgren, N., 1990. The DARPA TIMIT acoustic-phonetic continuous speech corpus CDROM. NTIS order number PB91-505065, October.
8. Glass, J., 1988. Finding acoustic regularities in speech: applications to phonetic recognition. Ph.D. thesis, EECS, MIT, May.
9. Glass, J., Chang, J., McCandless, M., 1996. A probabilistic framework for feature-based speech recognition. In: Proc. ICSLP Philadelphia, PA, pp. 2277-2280, October.
10. Glass, J., Hazen, T., Hetherington, L., 1999. Real-time telephone-based speech recognition in the Jupiter domain. In: Proc. ICASSP Phoenix, AZ, pp. 61-64, March.
11. Glass, J., Zue, V., 1988. Multi-level acoustic segmentation of continuous speech. In: Proc. ICASSP, New York, NY, pp. 429-432, April.
12. Halberstadt, A., 1998. Heterogeneous acoustic measurements and multiple classifiers for speech recognition. Ph.D. thesis, EECS, MIT, November.
13. Halberstadt, A., Glass, J., 1998. Heterogeneous measurements and multiple classifiers for speech recognition. In: Proc. ICSLP, Sydney, Australia, December, pp. 995-998.
14. Hazen, T., Halberstadt, A., 1998. Using aggregation to improve the performance of mixture Gaussian acoustic models. In: Proc. ICASSP, Seattle, WA, May, pp. 653-656.
15. Hazen, T., Seneff, S., Polifroni, J., 2002. Recognition confidence scoring and its use in speech understanding systems. Comp. Speech Lang. 16, 49-67.
16. Hetherington, L., 2001. An efficient implementation of phonological rules using finite-state transducers. In: Proc. Eurospeech, Aalborg, Denmark, September, pp. 1522-1609.
17. Holmes, W., Russell, M., 1996. Modeling speech variability with segmental HMMs. In: Proc. ICASSP, Atlanta, GA, May, pp. 447-450.
18. Lamel, L., Gauvain, J.L., 1993. High performance speaker-independent phone recognition using CDHMM. In: Proc. Eurospeech, Berlin, Germany, September, pp. 121-124.
19. Lee, K.F., Hon, H.W., 1989. Speaker-independent phone recognition using hidden Markov models. IEEE Trans. ASSP 37 (11), 1641-1648.
20. Lee, S., Glass, J., 1998. Real-time probabilistic segmentation for segment-based speech recognition. In: Proc. ICSLP, Sydney, Australia, December, pp. 1803-1806.
21. Livescu, K., Glass, J., 2001. Segment-based recognition on the PhoneBook task: initial results and observations on duration modeling. In: Proc. Eurospeech Aalborg, Denmark, September, pp. 1437-1440.
22. Ljolje, A., 1994. High accuracy phone recognition using context clustering and quasi-triphone models. Comput. Speech Lang. 8 (2), 129-151.
23. Marcus, J., 1993. Phonetic recognition in a segment-based HMM. In: Proc. ICASSP, Minneapolis, MN, April, pp. 479-482.
24. Mari, J.F., Fohr, D., Junqua, J.C., 1996. A second-order HMM for high performance word and phoneme-based continuous speech recognition. In: Proc. ICASSP, Atlanta, GA, May, pp. 435-438.
25. Ming, J., Smith, F., 1998. Improved phone recognition using Bayesian triphone models. In: Proc. ICASSP, Seattle, WA, May, pp. 409-412.
26. Ostendorf, M., Digilakis, V., Kimball, O., 1996. From HMM's to segment models: a unified view of stochastic modelling for speech recognition. IEEE Trans. Speech Audio Proc. 4 (5), 360-378.
27. Ostendorf, M., Roucos, S., 1989. A stochastic segment model for phoneme-based continuous speech recognition. IEEE Trans. ASSP 37 (12), 1857-1869.
28. Phillips, M., Glass, J., 1994. Phonetic transition modelling for continuous speech recognition. J. Acoust. Soc. Am. 95 (5), 2877.
29. Rabiner, L., 1989. A tutorial on hidden Markov models and selected applications in speech recognition. Proc. IEEE 77 (2), 257-286.
30. Riley, M., Ljolje, A., 1991. Lexical access with a statistically-derived phonetic network. In: Proc. Eurospeech Genoa, Italy, September, pp. 585-585.
31. Robinson, A., 1994. An application of recurrent nets to phone probability estimation. IEEE Trans. Neural Networks 5 (2), 298-305.
32. Robinson, T., Hochberg, M., Renals, S., 1994. IPA: improved phone modelling with recurrent neural networks. In: Proc. ICASSP, Adelaide, Australia, April, pp. 37-40.
33. Rohlicek, J., Russell, W., Roucos, S., Gish, H., 1989. Continuous hidden Markov modelling for speaker-independent word spotting. In: Proc. ICASSP, Glasgow, Scotland, May, pp. 627-630.
34. Roucos, S., Ostendorf, M., Gish, H., Derr, A., 1988. Stochastic segment modelling using the Estimate-Maximize algorithm. In: Proc. ICASSP, New York, NY, pp. 127-130.
35. Russell, M., 1993. A segmental HMM for speech pattern modelling. In: Proc. ICASSP, Minneapolis, MN, pp. 499-502.
36. Stevens, K., 1995. Applying phonetic knowledge to lexical access. In: Proc. Eurospeech, Madrid, Spain, pp. 3-11.
37. Ström, N., Hetherington, L., Hazen, T., Sandness, E., Glass, J., 1999. Acoustic modelling improvements in a segment-based speech recognizer. In: Proc. IEEE Automatic Speech Recognition and Understanding Workshop, Keystone, CO, December, pp. 139-142.
38. Weinstein, C., McCandless, S., Mondshein, L., Zue, V., 1975. A system for acoustic-phonetic analysis of continuous speech. IEEE Trans. ASSP 23, 54-67.
39. Wilpon, J., Rabiner, L., Lee, C.H., Goldman, E., 1990. Automatic recognition of keywords in unconstrained speech using hidden Markov models. IEEE Trans. ASSP 38 (11), 1870-1878.
40. Young, S., Woodland, P., 1994. State clustering in hidden Markov model-based continuous speech recognition. Comput. Speech Lang. 8 (4), 369-383.
41. Zhu, Q., Alwan, A., 2000. On the use of variable frame rate analysis in speech recognition. In: Proc. ICASSP, Istanbul, Turkey, June, pp. 1783-1786.
42. Zue, V., Glass, J., Phillips, M., Seneff, S., 1989. The MIT Summit speech recognition system: a progress report. In: Proc. Speech and Natural Language Workshop, Philadelphia, PA, February, pp. 179-189.
43. Zue, V., Seneff, S., Glass, J., Polifroni, J., Pao, C., Hazen, T., Hetherington, L., 2000. Jupiter: a telephone-based conversational interface for weather information. IEEE Trans. Speech Audio Proc. 8 (1), 85-96.