MINIMUM CLASSIFICATION ERROR LINEAR REGRESSION (MCELR) FOR SPEAKER ADAPTATION USING HMM WITH TREND FUNCTIONS

5th European Conference on Speech Communication and Technology, EUROSPEECH 1997

Volumn , Issue , 1997, Pages 2343-2346

  Chengalvarayan, Rathinavelu ^a  

^a LUCENT TECHNOLOGIES   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ERRORS; GRADIENT METHODS; LINEAR TRANSFORMATIONS; METADATA; SPEECH COMMUNICATION; SPEECH RECOGNITION;

GAUSSIANS; INTEGRATED APPROACH; MEAN FUNCTIONS; MINIMUM CLASSIFICATION ERROR; POLYNOMIAL COEFFICIENTS; RECOGNITION ERROR; SPEAKER ADAPTATION; TIME VARYING; TRANSFORMATION MATRIX; TREND FUNCTIONS;

LINEAR REGRESSION;

EID: 0347323000     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (15)

1. C. M. Ayer, M. J. Hunt and D. M. Brookes, "A Discriminatively Derived Linear Transform for Improved Speech Recognition", Proc. EUROSPEECH, Vol. 1, p p. 583-586, Berlin, September, 1993.
2. L. Deng, M. Aksmanovic, X. Sun and J. Wu, "Speech Recognition Using Hidden Markov Models with Polynomial Regression Functions as Nonstationary States", IEEE Trans, on Speech and Audio Processing, Vol.2, No. 4, pp. 507-520, October 1994.
3. T. Eisele, R. H. Umbach and D. Langmann, "A Comparative Study of Linear Feature Transformation Techniques for Automatic Speech Recognition", Proc. ICSLP, Vol. 1, pp. 252-255, Philadelphia, October 1996.
4. H. Gish and K. Ng, "Parametric Trajectory Models for Speech Recognition," Proceedings of ICSLP, Vol. 1, 1996, pp. 466-469.
5. F. T. Johansen and M. H. Johnsen, "Non-Linear Input Transformations for Discriminative HMMS", Proc. ICASSP, Vol. 1, pp. 225-228, Adelaide, 1994.
6. C. H. Lin, P. C. Chang and C. H. Wu, "An Initial Study on SPeaker Adaptation for Mandarin Syllable Recognition with Minimum Error Discriminative Training", Proc. ICSLP, Vol. 1, pp. 307-310, Yokohama, 1994.
7. C. S. Liu, C. H. Lee, W. Chou, B. H. Juang and A. Rosenberg, "A Study on Minimum Error Discriminative Training for Speaker Recognition", lournal of Acoustical Society of America, Vol. 97, No. 1, pp. 637-648, January, 1995.
8. T. Matsui and S. Furui, "A Study of Speaker Adaptation Based on Minimum Classification Error Training", Proc. EUROSPEECH, Vol. 1, pp. 81-84, Madrid, September, 1995.
9. M. Padmanabhan, L. Bahl, D. Nahamoo and M. Picheny, "Speaker Clustering and Transformation for Speaker Adaptation in Large-Vocabulary Speech Recognition Systems", Proc. ICASSP, Vol. 2, pp. 701-704, Atlanta, May 1996.
10. C. Rathinavelu and L. Deng, "Speaker Adaptation Experiments Using Nonstationary-State Hidden Markov Models: A MAP Approach", Proc. ICASSP, Vol. 2, pp. 1415-1418, Munich, April 1996.
11. C. Rathinavelu and L. Deng, "The Trended HMM with Discriminative Training for Phonetic Classification", Proc. ICSLP, Vol. 2, pp. 1049-1052, Philadelphia, October 1996.
12. C. Rathinavelu and L. Deng, "HMM-Based Speech Recognition Using State-Dependent, Discriminatively Derived Transforms on Mel-Warped DFT Features", IEEE Transactions on Speech and Audio Processing, Vol. 5, NO. 3, pp-243-256, May, 1997.
13. A. Sankar, L. Neumeyer and M. Weintraub, "An Experimental Study of Acoustic Adaptation Algorithms", Proc. ICASSP, Vol. 2, pp. 713-716, Atlanta, May 1996.
14. J. Takahashi and S. Sagayama, "Minimum Classification Error Training for a Small Amount of Data Enhanced by Vector-Field-Smoothed Bayesian Learning", Proc. ICASSP, Vol. 2, pp. 597-600, Atlanta, May 1996.
15. C. J. Leggetter and P. C. Woodland, "Maximum Likelihood Linear Regression for Speaker Adaptation of Continuous Density Hidden Markov Models", Computer Speech and Language, Vol. 9, pp. 171-185, 1995.