Log-linear framework for linear feature transformations in speech recognition

Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2009

Volumn , Issue , 2009, Pages 76-81

  Tahir, Muhammad Ali ^a   Heigold, Georg ^a   Plahl, Christian ^a   Schlüter, Ralf ^a   Ney, Hermann ^a  

^a RWTH AACHEN UNIVERSITY   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ACOUSTIC MODEL; CONVEX OPTIMIZATION PROBLEMS; DECORRELATIONS; DIMENSION REDUCTION; DISCRIMINATIVE TRAINING; LARGE VOCABULARY; LINEAR DISCRIMINANT ANALYSIS; LINEAR FEATURE; PRE-PROCESSING STEP;

CONVEX OPTIMIZATION; DISCRIMINANT ANALYSIS; LINEAR TRANSFORMATIONS; MATHEMATICAL TRANSFORMATIONS;

SPEECH RECOGNITION;

EID: 77949400206     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ASRU.2009.5373395     Document Type: Conference Paper

References (13)

1. R. Häb-Umbach and H. Ney, "Linear discriminant analysis for improved large vocabulary continuous speech recognition," in Proc. ICASSP'92, vol. 1, San Francisco, USA, Mar. 1992, pp. 13-16.
2. N. Kumar and A. G. Andreou, "Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognition," SPECOM, vol. 26, no. 4, pp. 283-297, Dec. 1998.
3. D. Povey, "Discriminative training for large vocabulary speech recognition," Ph.D. dissertation, Cambridge, England, 2004.
4. M. K. Omar and M. Hasegawa-Johnson, "Maximum conditional mutual information projection for speech recognition," in Proc. INTERSPEECH'03, Geneva, Switzerland, Sep. 2003.
5. D. Povey, B. Kingsbury, L. Mangu, G. Saon, H. Soltau, and G. Zweig, "fMPE: Discriminatively trained features for speech recognition," in Proc. ICASSP'05, Philadelphia, USA, May 2005.
6. M. Ferras, C. Leung, C. Barras, , and J. Gauvain, "Constrained MLLR for speaker recognition," in Proc. ICASSP'07, Honolulu, Hawaii, Apr. 2007.
7. G. Heigold, P. Lehnen, R. Schlüter, and H. Ney, "On the equivalence of Gaussian and log-linear HMMs," in Proc. INTERSPEECH'08, Brisbane, Australia, Sep. 2008.
8. M. Riedmiller and H. Braun, "A direct adaptive method for faster backpropagation learning: The RPROP algorithm," in Proc. ICNN'93, San Francisco, USA, 1993, pp. 586-591.
9. D. Kershaw, T. Robinson, and M. Hochberg, "Context-dependent classes in a hybrid recurrent network-HMM speech recognition system," in Proc. NIPS'96, Denver, USA, Nov. 1996, pp. 750-756.
10. G. Heigold, D. Rybach, R. Schlüter, and H. Ney, "Investigations on convex optimization using log-linear HMMs for digit string recognition," in Proc. INTERSPEECH'09, Brighton, U.K., Sep. 2009.
11. J. Darroch and D. Ratcliff, "Generalized iterative scaling for log-linear models," Annals of Mathematical Statistics, vol. 43, pp. 1470-1480, 1972.
12. L. Welling, "Merkmalsextraktion in spracherkennungssystemen für grossen wortschatz," Ph.D. dissertation, RWTH Aachen, Aachen, Germany, 1999.
13. R. Schlüter, A. Zolnay, and H. Ney, "Feature combination using linear discriminant analysis and its pitfalls," in Proc. INTERSPEECH'06, Sep. 2006, pp. 345-348.