A method of combining multiple probabilistic classifiers through soft competition on different feature sets

Neurocomputing

Volumn 20, Issue 1-3, 1998, Pages 227-252

  Chen, Ke ^a,b   Chi, Huisheng ^a  

^a PEKING UNIVERSITY   (China)

^b OHIO STATE UNIVERSITY   (United States)

Author keywords

Combination of multiple classifiers; Different feature sets; Expectation maximization (EM) algorithm; Soft competition; Speaker identification

Indexed keywords

COMPUTER SIMULATION; LEARNING ALGORITHMS; LEARNING SYSTEMS; MATHEMATICAL MODELS; PROBABILITY; SPEECH RECOGNITION;

EXPECTATION-MAXIMIZATION (EM) ALGORITHMS; MULTIPLE PROBABILISTIC CLASSIFIERS; SOFT COMPETITION;

NEURAL NETWORKS;

ACCURACY; ALGORITHM; ARTICLE; AUTOANALYSIS; COMPUTER NETWORK; DATA ANALYSIS; PRIORITY JOURNAL; PROBABILITY; SIMULATION; SPEECH;

EID: 0032584920     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(98)00019-8     Document Type: Article

References (46)

1. Agnew C. Multiple probability assessments by dependent experts. J. Amer. Statist. Assoc. 80(3):1985;343-347.
2. Atal B.S. Effectiveness of linear prediction characteristics of the speech waves for automatic speaker identification and verification. J. Acoust. Soc. Amer. 55(6):1974;1304-1312.
3. Battiti R., Colla A.M. Democracy in neural nets: voting schemes for classification. Neural Networks. 7(4):1994;691-708.
4. Bennani Y. A modular and hybrid connectionist system for speaker identification. Neural Comput. 7(4):1995;791-798.
5. Y. Bennani, P. Gallinari, Connectionist approaches for automatic speaker recognition, Proc. ESCA Workshop on Automatic Speaker Recognition, Identification and Verification, 1994, pp. 95-102.
6. Blum A. Selection of relevant features and examples in machine learning. Artif. Intell. 97(2):1997;245-272.
7. L. Breiman, Stacked regression, Tech. Rep. TR-367, Department of Statistics, University of California, Berkeley, 1992.
8. Breiman L. Bagging predictors. Mach. Learning. 26(2):1996;123-140.
9. Campbell F.P. Speaker recognition: a tutorial. Proc. IEEE. 85(9):1997;1437-1463.
10. Chatterjee S., Chatterjee S. On combining expert opinions. Amer. J. Math. Management Sci. 7(1):1987;271-295.
11. Chen K., Wang L., Chi H. Methods of combining multiple classifiers with different features and their applications to text-indpendent speaker identification. Int. J. Pattern Recognition Artif. Intell. 11(3):1997;417-445.
12. K. Chen, D. Xie, H. Chi, Speaker identification based on hierarchical mixture of experts, Proc. World Congress on Neural Networks, Washington DC, 1995, pp. I493-I496.
13. Chen K., Xie D., Chi H. A modified HME architecture for text-dependent speaker identification. IEEE Trans. Neural Networks. 7(5):1996;1309-1313.
14. Chen K., Xie D., Chi H. Speaker Identification using time-delay HMEs. Int. J. Neural Systems. 7(1):1996;29-43.
15. K. Chen, L. Xu, H. Chi, Improved learning algorithms for mixtures of experts in multiway classification, Neural Networks (1996) (in revision).
16. Dempster A.P., Laird N.M., Rubin D.B. Maximum-likelihood from incomplete data via the EM algorithm. J. Roy. Statist. Soc. B. 39(1):1977;1-38.
17. Doddington G. Speaker recognition - identifying people by their voice. Proc. IEEE. 73(11):1986;1651-1664.
18. Duda R., Hart P. Pattern Classification and Scene Analysis. 1973;Wiley, New York.
19. Y. Freund, R. Schapire, Experiments with a new boosting algorithm, Proc. 13th Int. Conf. Machine Learning, 1996, pp. 148-156.
20. S. Furui, An overview of speaker recognition technology, Proc. ESCA Workshop on Automatic Speaker Recognition, Identification and Verification, 1994, pp. 1-9.
21. Furui S. Recent advances in speaker recognition. Pattern Recognition Lett. 18(9):1997;859-872.
22. Gelfand A., Ballick B., Dey D. Modeling expert opinion arising as a partial probabilistic specification. J. Amer. Statist. Assoc. 90(5):1995;598-604.
23. S. Hashem, Optimal linear combinations of neural networks, Tech. Rep. SMS 94-4, School of Industrial Engineering, Purdue University, 1993.
24. J. He, L. Liu, G. Palm, A text-independent speaker identification system based on neural networks, Proc. Int. Conf. Spoken Language Processing, Yokohama, 1994, pp. 181-185.
25. Ho T., Hull J., Srihari S. Decision combination in multiple classifier systems. IEEE Trans. Pattern Anal. Mach. Intell. 16(1):1994;66-75.
26. Huang Y., Suen C. A method of combining multiple experts for the recognition of unconstrained handwritten numerals. IEEE Trans. Pattern Anal. Mach. Intell. 17(1):1995;90-94.
27. Jacobs R.A. Methods for combining experts' probability assessments. Neural Comput. 7(5):1995;867-888.
28. Jacobs R.A., Jordan M.I., Nowlan S.J., Hinton G.E. Adaptive mixtures of local experts. Neural Comput. 3(1):1991;79-87.
29. Ji C., Ma S. Combinations of weak classifiers. IEEE Trans. Neural Networks. 7(1):1997;32-42.
30. Jordan M.I., Jocobs R.A. Hierarchical mixture of experts and EM algorithm. Neural Comput. 6(2):1994;181-214.
31. Kanal L. On pattern, categories, and alternative realities. Pattern Recognition Lett. 14(3):1993;241-255.
32. M. LeBlanc, R. Tibshirani, Combining estimates in regression and classification, Tech. Rep., Department of Preventive Medicine and Biostatistics, University of Toronto, 1993.
33. R. Meir, Bias, variance, and the combination of estimators, Tech. Rep. 922, Department of Electrical Engineering, Technion, Haifa, Israel, 1994.
34. O'Shaughnessy D. Speaker recognition. IEEE ASSP Mag. 3(4):1986;4-17.
35. M.P. Perrone, Improving regression estimation: averaging methods of variance reduction with extensions to general convex measure optimization, Ph.D. Thesis, Department of Physics, Brown University, 1993.
36. Rabiner L.R., Juang B.H. Fundamentals of Speech Recognition. 1993;Englewood Cliffs, Prentice-Hall, New Jersey.
37. D.A. Reynolds, A Gaussian mixture modeling approach to text-independent speaker identification, Ph.D. Thesis, Department of Electrical Engineering, Georgia Institute of Technology, 1992.
38. Rogova G. Combining the results of several neural network classifiers. Neural Networks. 7(5):1994;777-781.
39. Sambur M.R. Selection of acoustic features for speaker identification. IEEE Trans. Acoust. Speech Signal Process. 23(1):1975;176-182.
40. Soong F.K., Rosenberg A.E. On the use of instantaneous and transitional spectral information in speaker recognition. IEEE Trans. Acoust. Speech Singal Process. 36(6):1988;871-879.
41. V. Tresp, M. Taniguchi, Combining estimators using non-constant weithting functions, in: G. Tesauro, D. Tourezsky, T. Leen (Eds.), Advances in Neural Information Processing Systems, MIT Press, Cambridge, MA, 1995, pp. 419-426.
42. Waibel A., Hanazawa T., Hinton G., Shikano K., Lang K. Phoneme recognition using time-delay neural networks. IEEE Trans. Acoust. Speech Signal Process. 37(3):1989;328-339.
43. Wolpert D.H. Stacked generalization. Neural Networks. 5(2):1992;241-259.
44. L. Xu, M.I. Jordan, EM learning on a generalized finite mixture model for combining multiple classifiers, Proc. World Congress on Neural Networks, San Diego, 1993, pp. IV227-IV230.
45. L. Xu, M.I. Jordan, G.E. Hinton, An alternative model for mixture of experts, in: G. Tesauro, D. Tourezsky, T. Leen (Eds.), Advances in Neural Information Processing Systems, MIT Press, Cambridge, MA, 1995.
46. Xu L., Krzyzak A., Suen C.Y. Methods of combining multiple classifiers and their applications to handwriting recognition. IEEE Trans. System Man. Cybernet. 23(3):1992;418-435.