Performance comparisons of all-pass transform adaptation with maximum likelihood linear regression

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

Volumn 1, Issue , 2004, Pages

  McDonough, John ^a   Waibel, Alex ^a  

^a UNIVERSITY OF KARLSRUHE   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

ADAPTIVE ALGORITHMS; ERROR ANALYSIS; GAUSSIAN NOISE (ELECTRONIC); LINEAR SYSTEMS; MARKOV PROCESSES; MATHEMATICAL MODELS; MATHEMATICAL TRANSFORMATIONS; MAXIMUM LIKELIHOOD ESTIMATION; OPTIMIZATION; REGRESSION ANALYSIS;

HIDEN MARKOV MODEL (HMM); MAXIMUM LIKELIHOOD LINEAR REGRESSION (MLLR); VOCAL TRACT LENGTH NORMALIZATION (VTLN); WORD ERROR RATES (WER);

SPEECH RECOGNITION;

EID: 4544375020     PISSN: 15206149     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (11)

1. A. Anastasakos, J. McDonough, R. Schwartz, and J. Makhoul. A compact model for speaker-adaptive training. In Proc. ICSLP, 1996.
2. Andreas Andreou, Theresa Kamm, and Jordan Cohen. Experiments in vocal tract normalization. In Proc. CAIP Work-shop: Frontiers in Speech Recognition II, 1994.
3. Keinosuke Fukunaga. Statistical Pattern Recognition. Academic Press, San Diego, second edition, 1990.
4. M. J. F. Gales. Semi-tied covariance matrices for hidden markov models. IEEE Transaction on Speech and Audio Processing, 7:272-281, 1999.
5. N. Kumar and A. G. Andreou. Heteroscedastic discriminant analysis and reduced rank HMMs for improved speech recognition. Speech Communication, 26:283-297, 1998.
6. C. J. Leggetter and P. C. Woodland. Maximum likelihood linear regression for speaker adaptation of continuous density hidden markov models. Computer Speech and Language, pages 171-185, 1995.
7. John McDonough, Thomas Schaaf, and Alex Waibel. Speaker adaptation with all-pass transforms. Speech Communication, Special Issue on Adaptation Methods for Speech Recognition, 42:75-91, January 2004.
8. John W. McDonough. Speaker Compensation with All-Pass Transforms. PhD thesis, The Johns Hopkins University, Baltimore, MD, 2000.
9. John W. McDonough. Performance comparisons of all-pass transform adaptation with maximum likelihood linear regression. Technical Report 102, Interactive Systems Laboratories, University of Karslruhe, 2003.
10. A. V. Oppenheim and R. W. Schafer. Discrete-Time Signal Processing. Prentice-Hall, Englewood Cliffs, New Jersey, 1989.
11. L. Uebel and P. Woodland. Improvements in linear transform based speaker adaptation. In Proc. ICASSP, 2001.