Discriminative Training of Dynamic Programming Based Speech Recognizers

IEEE Transactions on Speech and Audio Processing

Volumn 1, Issue 2, 1993, Pages 135-143

  Juang, Biing Hwang ^b  

^a Ministry of Transportation and Communications Taiwan   (Taiwan)

^b LUCENT TECHNOLOGIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; DATA REDUCTION; DYNAMIC PROGRAMMING; ERROR ANALYSIS; LEARNING SYSTEMS; MATHEMATICAL MODELS; NEURAL NETWORKS; OPTIMIZATION; PARAMETER ESTIMATION; PROBABILITY; SIGNAL DISTORTION; SPEECH ANALYSIS;

DISCRIMINATIVE TRAINING; DYNAMIC PROGRAMMING BASED SPEECH RECOGNIZERS; DYNAMIC TIME WARPING (DTW) BASED SYSTEM; GENERALIZED PROBABILISTIC DESCENT (GPD) ALGORITHM; MAXIMUM A POSTERIORI (MAP); RECOGNITION ERROR;

SPEECH RECOGNITION;

EID: 0027579316     PISSN: 10636676     EISSN: None     Source Type: Journal    
DOI: 10.1109/89.222873     Document Type: Article

References (18)

1. D.E.Rumelhart et al., Parallel Distributed Processing (PDP): Exploration in the Microstructure of Cognition(Vol.1).Cambridge, MA:MIT Press, 1986.
2. R. P. Lippmann, “An introduction to computing ith neural nets,” IEEE ASSP Mag., pp. 4–22, Apr. 1987.
3. T. Kohonen, G. Bama, and R. Chrisley, “Statistical pattern recognition ith neural netorks: Benchmarking Studies,” in Proc. IEEE ICNN, vol. 1, pp. 61–68, July 1988.
4. E. McDermott and S. Katagiri, “Shift-invariant multi-category phoneme recognition using Kohonen’s LVQ2,” in ICASSP-89, pp. 81–84.
5. S. Katagiri, C. H. Lee, and B. H. Juang, “A theory on adaptive training for pattern classification,” to be published.
6. Wu Chou and B. H. Juang, “Adaptive discriminative learning in pattern recognition,” Tech. Rep., AT&T Bell Lab., Murray Hill NJ
7. B. H. Juang and S. Katagiri, “Discriminative learning for minimum error classification,” Tech. Rep. AT&T Bell Lab., Murray Hill, NJ.
8. u Chou, B. H. Juang, and C. H. Lee, “Segmental GPD training of HMM base speech recognizer,” in Proc. ICASSP-92, San Francisco, CA, Mar. 1992.
9. N. J. Nilsson, Learning Machines: Foundations of Trainable Pattern-Classifying Systems. Ne York: McGraHill, 1965.
10. S. Agmon, “The relaxation method for linear inequalities,” Can. J. Math., vol. 6, pp. 382–392, 1954.
11. Y. C. Ho and R. L. Kashyap, “An algorithm for linear inequalities and its applications,” IEEE Trans. Elec. Comp., vol. EC-14, pp. 683–688, Oct. 1965.
12. R.O.Duda and P. E. Hart, Pattern Classification and Scene Analysis. Ne York:Wiley, 1973.
13. J. G. wilpon and L. R. Rabiner, “A modified K-means clustering algorithm for use in isolated ord recognition,” IEEE Trans. Acoust., Speech, Signal Processing, pp. 587–594, 1985.
14. P. C. Chang, S. H. Chen, and B. H. Juang, “Discriminative analysis of distortion sequences in speech recognition,” presented at the ICASSP-91, 1991.
15. S. Katagiri, C. H. Lee, and B. H. Juang, “Ne discriminative training algorithms based on the generalized probabilistic descent method,” in Proc. 1991 IEEE orkshop on Neural Netorks for Signal Processing, pp. 299–308, Princeton, NJ, Sept. 1991.
16. T. Komori and S. Katagiri, “A ne discriminative training algorithm for dynamic time arping speech recognition,” IEICE Tech. Rep., SP91-10, pp. 33–40, Japan, June 1991.
17. B. H. Juang, L. R. Rabiner, and J. G. Wilpon, “On the use of bandpass liftering in speech recognition,” IEEE Trans. Acousr. Speech, Signal Processing, vol. 35, pp. 947-954, 1987.
18. F. K. Soong and A. E. Rosenberg, On the use of instantaneous and transitional spectral information in speaker recognition, IEEE Trans.Acousf. Speech, Signal Processing, vol. 36, pp. 871-879, 1988.