Speaker adaptation with all-pass transforms

Speech Communication

Volumn 42, Issue 1, 2004, Pages 75-91

  McDonough, John ^a   Schaaf, Thomas ^a   Waibel, Alex ^a  

^a UNIVERSITY OF KARLSRUHE   (Germany)

Author keywords

Speaker adaptation; Speech recognition

Indexed keywords

ERROR COMPENSATION; MARKOV PROCESSES; MATHEMATICAL TRANSFORMATIONS; MAXIMUM LIKELIHOOD ESTIMATION; PARAMETER ESTIMATION; PROBABILITY DENSITY FUNCTION; REGRESSION ANALYSIS; SPEECH COMMUNICATION;

BILINEAR TRANSFORMS (BT); EXPECTATION MAXIMIZATION (EM) ALGORITHM; SPEAKER ADAPTATION;

SPEECH RECOGNITION;

EID: 0347269184     PISSN: 01676393     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.specom.2003.09.005     Document Type: Conference Paper

References (41)

1. Acero, A., 1990. Acoustical and environmental robustness in automatic speech recognition. Ph.D. thesis, Carnegie Mellon University, Pittsburgh, PA.
2. Anastasakos, T., McDonough, J., Schwartz, R., Makhoul, J., 1996. A compact model for speaker-adaptive training. In: Proc. ICSLP.
3. Andreou, A., Kamm, T., Cohen, J., 1994. Experiments in vocal tract normalization. In: Proc. CAIP Workshop: Frontiers in Speech Recognition II.
4. Bocchieri, E., Digalakis, V., Corduneanu, A., Boulis, C., 1999. Correlation modeling of MLLR transform biases for rapid HMM adaptation to new speakers. In: Proc. ICASSP, Vol. II, pp. 773-776.
5. Churchill R.V., Brown J.W. Complex Variables and Applications. fifth ed. 1990;McGraw-Hill, New York.
6. Dempster A.P., Laird N.M., Rubin D.B. Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Statist. Soc. 39B:1977;1-38.
7. Digalakis V., Rtischev D., Neumeyer L. Fast speaker adaptation using constrained estimation of gaussian mixtures. IEEE Trans. Speech Audio Process. 3:1995;357-366.
8. Digalakis, V., Berkowitz, S., Bocchieri, E., Boulis, C., Byrne, W., Collier, H., Corduneanu, A., Kannan, A., Khudanpur, S., Sankar, A., 1996. Rapid speech recognizer adaptation to new speakers. In: Proc. ICASSP, Vol. I, pp. 339-341.
9. Ding, G.-H., Zhu, Y.-F., Li, C., Xu, B., 2002. Implementing vocal tract length normalization in the MLLR framework. In: ICSLP, pp. 1389-1392.
10. Eide, E., Gish, H., 1996. A parametric approach to vocal tract length normalization. In: Proc. ICASSP, Vol. I, pp. 346-348.
11. Gales M.J.F. Maximum likelihood linear transformations for HMM-based speech recognition. Computer Speech Language. 12:1998;75-98.
12. Gales M.J.F. Semi-tied covariance matrices for hidden markov models. IEEE Trans. Speech Audio Process. 7:1999;272-281.
13. Gales M.J.F., Woodland P.C. Mean and variance adaptation within the MLLR framework. Computer Speech Language. 10:1996;249-264.
14. Gill P.E., Murray W., Wright M.H. Practical Optimization. 1981;Academic Press, London.
15. Gunawardana, A., Byrne, W., 2000. Robust estimation for rapid speaker adaptation using discounted likelihood techniques, IEEE ICASSP, 5-9 June 2000, Vol. 2, pp. II985-II988.
16. Hermansky H. Perceptual linear predictive (PLP) analysis of speech. J. Acoust. Soc. Am. 87(4):1990;1738-1752.
17. Kannan, A., Khudanpur, S., 1996. Tree-structured models of parameter dependence for rapid adaptation in large vocabulary conversational speech recognition. In: Proc. ICASSP, Vol. II, pp. 769-772.
18. Kuhn R., Junqua J.-C., Nguyen P., Niedzielski N. Speaker adaptation in eigenvoice space. IEEE Trans. Speech Audio Process. 8(6):2000;695-707.
19. Kumar N., Andreou A.G. Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognition. Speech Commun. 26:1998;238-297.
20. Lee, L., Rose, R.C., 1996. Speaker normalization using efficient frequency warping procedures. In: Proc. ICASSP, Vol. I, pp. 353-356.
21. Leggetter C.J., Woodland P.C. Maximum likelihood linear regression for speaker adaptation of continuous density hidden Markov models. Computer Speech Language. 9:1995;171-185.
22. Luenberger D.G. Linear and Nonlinear Programming. second ed. 1984;Addison-Wesley, New York.
23. Masry E., Stieglitz K., Liu B. Bases in hilbert space related to the representation of stationary operators. SIAM J. Appl. Math. 16:1968;552-562.
24. McDonough, J.W., 1998. On the estimation of optimal regression classes for speaker adaptation. Tech. Rep. 36, Center for Language and Speech Processing, The Johns Hopkins University.
25. McDonough, J.W., 1999. The Homewood extensions. Tech. Rep. 39, Center for Language and Speech Processing, The Johns Hopkins University, Baltimore, MD.
26. McDonough, J.W., 2000. Speaker compensation with all-pass transforms. Ph.D. thesis, The Johns Hopkins University, Baltimore, MD.
27. McDonough, J.W., 2001. On maximum mutual information speaker-adapted training. Tech. Rep. 103, Universität Karlsruhe.
28. McDonough, J., Waibel, A., 2003. Performance comparisons of all-pass transform adaptation with maximum likelihood linear regression. Tech. Rep. 102, Universität Karlsruhe.
29. McDonough, J.W., Byrne, W., 1999. Single-pass adapted training with all-pass transforms. In: Proc. Eurospeech.
30. McDonough, J., Byrne, W., Luo, X., 1998. Speaker normalization with all-pass transforms. In: Proc. ICSLP.
31. Oppenheim A.V., Johnson D.H. Discrete-time representation of signals. Proc. IEEE. 60(6):1972;681-691.
32. Oppenheim A.V., Schafer R.W. Discrete-Time Signal Processing. 1989;Prentice-Hall, Englewood Cliffs, NJ.
33. Pitz, M., Molau, S., Schlüter, R., Ney, H., 2001. Vocal tract normalization equals linear transformation in cepstral space. In: Eurospeech, pp. 721-724.
34. Pye, D., Woodland, P.C., 1997. Experiments in speaker normalisation and adaptation for large vocabulary speech recognition. In: Proc. ICASSP, Vol. II, pp. 1047-1050.
35. Sankar A., Lee C.-H. A maximum-likelihood approach to stochastic matching for robust speech recognition. IEEE Trans. Speech Audio Process. 4(3):1996;190-201.
36. Saon, G., Zweig, G., Padmanabhan, M., 2000. Maximum likelihood discriminant feature spaces. In: Proc. ICASSP.
37. Shikano, K., 1986. Evaluation of LPC spectral matching measures for phonetic unit recognition. Tech. Rep., Computer Science Department, Carnegie Mellon University, Pittsburgh, PA.
38. Wegmann, S., McAllaster, D., Orloff, J., Peskin, B., 1996. Speaker normalization on conversational telephone speech. In: Proc. ICASSP, Vol. I, pp. 339-341.
39. Woodland, P., Povey, D., 2000. Large scale discriminative training for speech recognition. In: ISCA ITRW Automatic Speech Recognition: Challenges for the Millenium, pp. 7-16.
40. Young S., Odell J., Ollason D., Valtchev V., Woodland P. The HTK Book. 1999;Entropic Software, Cambridge.
41. Zue, V., 1971. Translation of divers' speech using digital frequency warping. Tech. Rep. 101, Res. Lab. Eltron., Massachusetts Institute of Technology, Cambridge, MA.