Assessing the importance of the segmentation probability in segment-based speech recognition

Speech Communication

Volumn 24, Issue 1, 1998, Pages 51-72

  Verhasselt, J ^a   Illina, I ^b   Martens, J P ^a   Gong, Y ^b   Haton, J P ^b  

^a GHENT UNIVERSITY   (Belgium)

^b INRIA   (France)

Author keywords

Posterior segment modeling formalism; Segment based speech recognition; Segmentation probability

Indexed keywords

ALGORITHMS; MATHEMATICAL MODELS; PROBABILITY; VECTORS;

SEGMENT BASED SPEECH RECOGNITION; SPEECH SEGMENTATION;

SPEECH RECOGNITION;

EID: 0032048095     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(97)00064-2     Document Type: Article

References (43)

1. Afify, M., Gong, Y., Haton, J.-P., 1995. Stochastic trajectory model for speech recognition: an extension to modeling time correlation. In: Proc. Eurospeech, Vol. 1, pp. 515-518.
2. Austin, S., Zavaliagkos, G., Makhoul, J., Schwartz, R., 1992. Speech recognition using segmental neural nets. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 625-628.
3. Bourlard, H., Morgan, N., 1994. Connectionist Speech Recognition: A Hybrid Approach. Kluwer Academic Publishers, Dordrecht.
4. Cerisara, C., Gong, Y., Haton, J.-P., 1996. Reconnaissance de la parole continue par le modèle STM polynomial. Actes des 21-èmes Journées d'Études sur la Parole, pp. 317-320.
5. Chang, J., Glass, J., 1997. Segmentation and modeling in segment-based recognition. In: Proc. Eurospeech, Vol. 3, pp. 1199-1202.
6. Flammia, G., Dalsgaard, P., Andersen, O., Lindberg, B., 1992. Segment based variable frame rate speech analysis and recognition using a spectral variation function. In: Proc. ICSLP, pp. 983-986.
7. Glass, J., Chang, J., McCandless, M., 1996. A probabilistic framework for feature-based speech recognition. In: Proc. ICSLP, Vol. 4, pp. 2277-2280.
8. Goldenthal, W., 1994. Statistical trajectory models for phonetic recognition. PhD Thesis, Laboratory for Computer Science MIT.
9. Gong, Y., 1997. Stochastic trajectory modeling and sentence searching for continuous speech recognition. IEEE Trans. Speech Audio Process. 5 (1), 33-34.
10. Gong, Y., Haton, J.-P., 1992. DTW-based phonetic labeling using explicit phoneme duration constraints. In: Proc. ICSLP, Vol. 2, pp. 863-866.
11. Gong, Y., Haton, J.-P., 1993. Iterative transformation and alignment for speech labeling. In: Proc. Eurospeech, Vol. 3, pp. 1759-1762.
12. Gong, Y., Haton, J.-P., 1994. Stochastic trajectory modeling for speech recognition. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 57-60.
13. Gong, Y., Illina, I., Haton, J.-P., 1996. Modeling long term variability information in mixture stochastic trajectory framework. In: Proc. ICSLP, Vol. 1, pp. 334-337.
14. Gosselin, B., 1996. Multilayer perceptrons combination applied to handwritten character recognition. Neural Process. Lett. 3, 3-10.
15. Hashem, S., 1997. Optimal linear combinations of neural networks. Neural Networks 10 (4), 599-614.
16. Illina, I., Gong, Y., 1996. Stochastic trajectory model with state-mixture for continuous speech recognition. In: Proc. ICSLP, Vol. 1, pp. 342-345.
17. Katke, W., 1985. Learning language using a pattern recognition approach. The AI Magazine, 64-73.
18. Kimball, O., 1995. Segment modeling alternatives for continuous speech recognition. PhD Thesis, Boston University College of Engineering.
19. Lamel, L., 1988. Formalizing knowledge used in spectrogram reading: Acoustic and perceptual evidence from stops. PhD Thesis, MIT.
20. Lamel, L., Gauvain, J.L., 1993. High performance speaker-independent phone recognition using CDHMM. In: Proc. Eurospeech, Vol. 1, pp. 121-124.
21. Lee, K.F., Hon, H.-W., 1989. Speaker-independent phone recognition using hidden markov models. IEEE Trans. Acoust. Speech Signal Process. 37 (11), 1641-1648.
22. Leung, H.C., 1989. The use of artificial neural networks for phonetic recognition. PhD Thesis, MIT Department of Electrical Engineering and Computer Science.
23. Leung, H.C., Glass, J.R., Phillips, M.S., Zue, V.W., 1990. Detection and classification of phonemes using context-independent error back-propagation. In: Proc. ICSLP, Vol. 2, pp. 1061-1064.
24. Leung, H.C., Hetherington, I.L., Zue, V.W., 1991. Speech recognition using stochastic explicit-segment modeling. In: Proc. Eurospeech, Vol. 2, pp. 931-934.
25. Leung, H.C., Hetherington, I.L., Zue, V.W., 1992. Speech recognition using stochastic segment neural networks. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 613-616.
26. 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. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 435-438.
27. Martens, J.-P., 1994. A connectionist approach to continuous speech recognition. In: Proc. FORWISS/CRIM ESPRIT Workshop, pp. 26-33.
28. Martens, J.P., Depuydt, L., 1991. Broad phonetic classification and segmentation of continuous speech by means of neural network and dynamic programming. Speech Communication 10, 81-90.
29. Martens, J.-P., Van Immerseel, L., 1990. An auditory model based on the analysis of envelope patterns. In: Proc. Internat. Conf. Acoust. Speech Signal Process., pp. 401-404.
30. Ostendorf, M., Roukos, S., 1989. A stochastic segment model for phoneme-based continuous speech recognition. IEEE Trans. Acoust. Speech Signal Process. 37, 1857-1869.
31. Ostendorf, M., Digalakis, V., Kimball, O., 1996. From HMM's to segment models: A unified view of stochastic modeling for speech recognition. IEEE Trans. Speech Audio Process. 4 (5), 360-378.
32. Rabiner, L., Wilpon, J., Juang, B.-H., 1986. A segmental k-means training procedure for connected word recognition. AT&T Tech. J. 65 (3), 21-40.
33. Richard, M., Lippmann, R., 1991. Neural network classifiers estimate Bayesian a posteriori probabilities. Neural Computation 3, 461-483.
34. Robinson, A.J., 1994. An application of recurrent nets to phone probability estimation. IEEE Trans. Neural Networks 5 (2), 298-305.
35. Rumelhart, D.E., Hinton, G.E., Williams, R.J., 1986. Learning internal representations by error propagation. In: Rumelhart, D.E., McClelland, J.L. (Eds.), Parallel Distributed Processing: Exploration of the Microstructure of Cognition, Vol. 1: Foundations. MIT Press, Cambridge, MA.
36. Siohan, O., Gong, Y., 1996. A semi-continuous stochastic trajectory model for phoneme-based continuous speech recognition. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 471-474.
37. Van Immerseel, L.M., Martens, J.-P., 1992. Pitch and voiced/unvoiced determination with an auditory model. J. Acoust. Soc. Amer. 91 (6), 3511-3526.
38. Vereecken, H., Martens, J.-P., 1996. Noise suppression and loudness normalization in an auditory model-based acoustic front-end. In: Proc. ICSLP, Vol. 1, pp. 566-569.
39. Verhasselt, J., Martens, J.-P., Baeyens, B., 1996. Speech recognition using a discriminative context-independent, segment-based speech recognizer. In: Proc. IEEE ProRISC, pp. 367-372.
40. Verhasselt, J., Illina, I., Martens, J.-P., Gong, Y., Haton, J.-P., 1997. The importance of segmentation probability in segment based speech recognizers. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 2, pp. 1407-1410.
41. Werbos, P.J., 1974. Beyond regression: New tools for prediction and analysis in the behavioral sciences. PhD Thesis, Harvard University, Cambridge, MA.
42. Xu, L., Krzyżak, A., Suen, C.Y., 1992. Methods of combining multiple classifiers and their applications to handwriting recognition. IEEE Trans. Syst. Man Cybernet. 22 (3), 418-435.
43. Zue, V., Glass, J., Phillips, M., Seneff, S., 1989. Acoustic segmentation and phonetic classification in the SUMMIT system. In: Proc. Internat. Conf. Acoust. Speech Signal Process., Vol. 1, pp. 389-392.