Discriminative feature weighting for HMM-based continuous speech recognizers

Speech Communication

Volumn 38, Issue 3-4, 2002, Pages 267-286

  De la Torre, Ángel ^a   Peinado, Antonio M ^a   Rubio, Antonio J ^a   Segura, José C ^a   Benítez, Carmen ^a  

^a UNIVERSITY OF GRANADA   (Spain)

Author keywords

Continuous speech recognition; Cost function; Discriminative feature extraction; Discriminative feature weighting; Error rate; Hidden Markov model; Minimum classification error; Probability density function

Indexed keywords

ACOUSTIC WAVES; GAUSSIAN NOISE (ELECTRONIC); MARKOV PROCESSES; VECTORS;

CONTINUOUS SPEECH RECOGNIZERS (CSR);

CONTINUOUS SPEECH RECOGNITION;

EID: 0036836832     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0167-6393(01)00068-1     Document Type: Article

References (43)

1. Bacchiani M., Aikawa K. Optimization of time-frequency masking filters using minimum classification error criterion. Proc. Internat. Conf. on Acoust. Speech Signal Process., ICASSP-94. Vol. 2:1994;275-278.
2. Bahl L.R., Brown P.F., de Souza P.V., Mercer R.L. Maximum mutual information estimation of hidden Markov models parameters for speech recognition. Proc. ICASSP-86, Tokyo. 1986;49-52.
3. Biem A., Katagiri S. Feature extraction based on minimum classification error/generalized probabilistic descent method. Proc. ICASSP-93. Vol. 2:1993;275-278.
4. Biem A., Katagiri S. Filter bank design based on discriminative feature extraction. Proc. ICASSP-94. Vol. 1:1994;485-488.
5. Biem A., Katagiri S. Cepstrum-based filter bank design using discriminative feature extraction training at various levels. Proc. Internat. Conf. on Acous. Speech Signal Process., ICASSP-97. Vol. 2:1997;1503-1506.
6. Biem A., Katagiri S., Juang B.H. Pattern recognition using discriminative feature extraction. IEEE Trans. Signal Process. 45(2):1997;500-504.
7. Biem A., McDermott E., Katagiri S. Discriminative filter bank model for speech recognition. Proc. EuroSpeech-95. Vol. 1:1995;545-548.
8. Casacuberta F., Garcia R., Llisterri J., Nadeu C., Pardo J.M., Rubio A. Development of spanish corpora for speech research (albayzin). Proc. Workshop Internat. Cooperation and Standarization of Speech Databases and Speech I/O Assessment Methods, September. 1991;26-28.
9. Chou W., Juang B.H., Lee C.H. Segmental gpd training of hmm based speech recognizer. Proc. ICASSP-92. 1992;I, 473-476.
10. Davis S.B., Mermelstein P. Comparison of parametric representations for monosyllabic word recognition in continuosly spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28(4):1980;357-366.
11. Di;́az-Verdejo J.E., Peinado A.M., Rubio A.J., Segarra E., Prieto N., Casacuberta F. Albayzin: a task-oriented spanish speech corpus. Proc. First Internat. Conf. on Language Resources and Evaluation LREC-98. Vol. 1:1998;497-501.
12. de la Torre A., Peinado A.M., Rubio A.J., Segura J.C., Sánchez V.E. Minimum classification error transformation for improving speech recognition systems. Proc. EUSIPCO-96. Vol. 3:1996;1575-1578.
13. de la Torre A., Peinado A.M., Rubio A.J., Sánchez V.E., Díaz J.E. An application of minimum classification error to feature space transformations for speech recognition. Speech Communication. 20(3-4):1996;273-290.
14. de la Torre A., Peinado A.M., Rubio A.J., Garcia P. Discriminative feature extraction for speech recognition in noise. Proc. EuroSpeech-97. Vol. 1:1997;291-294.
15. Duda R.O., Hart P.E. Pattern Classification and Scene Analysis. 1973;Wiley, New York.
16. Fukunaga K. Introduction to Statistical Pattern Recognition. 1990;Academic Press, New York.
17. Furui S. Speaker-independent isolated word recognition using dynamic features of speech spectrum. IEEE Trans. ASSP. 34(February):1986;52-59.
18. Huang X.D., Jack M.A. Unified techniques for vector quantisation and hidden markov modeling using semi-continuous models. Proc. ICASSP-89, Glasgow (Scotland), May. 1989;639-642.
19. Huang X., Lee K.F., Hon H.W. On semi-continuous hidden markov modeling. Proc. ICASSP-90. 1990;689-692.
20. Jin Q., Waibel A. Application of lda to speaker recognition. Proc. ICSLP-00. Vol. 2:2000;250-253.
21. Juang B.H., Katagiri S. Discriminative learning for minimum error classification. IEEE Trans. Signal Process. 40(12):1992;3043-3054.
22. Juang B.H., Rabiner L.R., Wilpon J.G. On the use of bandpass liftering in speech recognition. IEEE Trans. ASSP. 35(7):1987;947-954.
23. Juang B.H., Chou W., Lee C.H. Minimum classification error rate methods for speech recognition. IEEE Trans. Speech Audio Process. 5(3):1997;257-265.
24. Junqua J.C., Wakita H. A comparative study of cepstral lifters and distance measures for all pole models of speech in noise. Proc. ICASSP-89. 1989;476-479.
25. Kumar N., Andreou A.G. Heteroscedastic discriminant analysis and reduced rank hmms for improved speech recognition. Speech Communication. 26:1998;283-297.
26. Lee C.H., Rabiner L.R., Pieraccini R., Wilpon J.G. Acoustic modeling for large vocabulary speech recognition. Comput. Speech Language. 4:1990;127-165.
27. Lee K.F. Context-dependent phonetic hidden markov models for speaker-independent continuous speech recognition. IEEE Trans. ASSP. 38:1990;599-623.
28. Llisterri, J., Aguilar, L., Blecua, B., Machuca, M., Mota, C., Ríos, A., Moreno, A., 1993. Spanish eurom. 1. Esprit Project 6819 (SAM-A).
29. McDermott E., Katagiri S. Protoype-based minimum classification error/generalized probabilistic descent training for various speech units. Comput. Speech Language. 8(4):1994;351-368.
30. Milner B. Cepstral-time matrices and lda for improved connected digit and sub-word recognition accuracy. Proc. EuroSpeech-97. Vol. 1:1997;405-408.
31. Moreno P.J., Eberman B. A new algorithm for robust speech recognition: the delta vector taylor series approach. Proc. EuroSpeech-97. Vol. 5:1997;2599-2602.
32. Paliwal K.K., Bacciani M., Sagisaka Y. Minimum classification error training algorithm for feature extractor and pattern classifier in speech recognition. Proc. EuroSpeech-95. Vol. 1:1995;541-544.
33. Peinado A.M., Ramesh P., Roe D.B. On the use of energy information for speech recognition using HMM. Proc. EUSIPCO-90, Barcelona, September. Vol. 2:1990;1243-1246.
34. Peinado A.M., Rubio A.J., Segura J.C., Sánchez V., Díaz J.E. Mce estimation of vq parameters for mvqhmm speech recognition. Proc. EuroSpeech-95. Vol. 1:1995;533-536.
35. Peinado A.M., Segura J.C., Rubio A.J., García P., Pérez J.L. Discriminative codebook design using multiple vector quantization in hmm-based speech recognizers. IEEE Trans. Speech Audio Process. 4(2):1996;88-95.
36. Rabiner L.R., Juang B.H. Fundamentals of Speech Recognition. 1993;Prentice-Hall, Englewood Cliffs, NJ.
37. Rubio A.J., García P., de la Torre A., Segura J.C., Díaz-Verdejo J., Benítez M.C., Sánchez V., Peinado A.M., López-Soler J.M., Pérez Córdoba J.L. Stacc: an automatic service for information access using csr through telephone line. Proc. EuroSpeech-97. Vol. 4:1997;1779-1782.
38. Segura J.C., Rubio A.J., Peinado A.M., García P., Román R. Multiple VQ hidden Markov modeling for speech recognition. Speech Communication. 14(2):1994;163-170.
39. Tohkura Y. A weighted cepstral distance measure for speech recognition. IEEE Trans. ASSP. 35(10):1987;1414-1422.
40. Watanabe H., Yamaguchi T., Katagiri S. Discriminative metric design for pattern recognition. Proc. ICASSP-95. 1995;3439-3442.
41. Watanabe H., Yamaguchi T., Katagiri S. Discriminative metric design for robust pattern recognition. IEEE Trans. Signal Process. 45(11):1997;2655-2662.
42. Young S. A review of large-vocabulary continuous speech recognition. IEEE Signal Process. Magazine. 13(5):1996;45-57.
43. Young, S., Odell, J., Ollason, D., Valtchev, V., Woodland, P., 1997. The HTK Book, Cambridge University.