Model compensation and matched condition methods for robust speech recognition

Noise Reduction in Speech Applications

Volumn , Issue , 2002, Pages 245-276

  Singh, Rita ^a   Raj, Bhiksha ^b   Stern, Richard M ^c  

^a Carnegie Mellon University ^*  (United States)

^b MITSUBISHI ELECTRIC RESEARCH LABORATORIES   (United States)

^c CARNEGIE MELLON UNIVERSITY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 85009213257     PISSN: None     EISSN: None     Source Type: Book    
DOI: None     Document Type: Chapter

References (26)

1. Juang, B.H., Levinson, S.E., and Sondhi, M.M., Maximum likelihood estimation for multivariate mixture observations of Markov chains, IEEE Trans. Info. Theory, IT-32(2), 307–309, 1986.
2. Brand, M., Structure discovery in conditional probability models via an entropic prior and parameter extinction, Neural Comput., 11, 1155–1183, 1999.
3. Viterbi, A.J., Error bounds for convolutional codes and an asymptotically optimal decoding algorithm, IEEE Trans. Info. Theory, IT-13, 260–269, 1967.
4. Varga, A.P. and Moore, R.K., Hidden Markov model decomposition of speech and noise, Proc. ICASSP90, 1990, 845–848.
5. Leggetter, C.J. and Woodland, P.C., Speaker adaptation of HMMs using linear regression, Techn. Rep. CUED/F-INFENG/TR. 181, Cambridge University, Cambridge, U.K., 1994.
6. Gauvain, J.-L. and Lee C.-H., Maximum a posteriori estimation for multivariate Gaussian mixture observations of Markov chains, IEEE Trans. on Speech and Audio Processing, 2(2), 291–298, 1994.
7. Lasry, M.J. and Stern, R.M., A posteriori estimation of correlated jointly Gaussian mean vectors, IEEE Trans. on Pattern Anal. and Mach. Intel., 6, 530–535, 1984.
8. Zavaliagkos, G., Maximum a posteriori Adaptation Techniques for Speech Recognition, Ph.D. thesis, Northeastern University, Boston, 1995.
9. Gales, M.J.F., Model-Based Techniques for Noise Robust Speech Recognition, Ph.D. thesis, Cambridge University, Cambridge, U.K., 1996.
10. Dempster, A.P., Laird, N.M., and Rubin, D.B., Maximum likelihood from incomplete data via the EM algorithm (with discussion), J. Royal Stat. Soc., Series B, 39, 1–38, 1977.
11. Duda, R.O., Hart, P.E., and Stork, D.G., Pattern Classification, 2nd ed., John Wiley & Sons, New York, 2000.
12. Lippmann, R.P., Martin E.A., and Paul, D.B., Multi-style training for robust isolated-word speech recognition, Proc. ICASSP87, 1987, 705–708.
13. Cooke, M.P., Morris, A., and Green, P.D., Missing data techniques for robust speech recognition, Proc. ICASSP97, 1997, 863–866.
14. Josifovski, L., Cooke, M., Green, P., and Vizinho, A., State based imputation of missing data for robust speech recognition and speech enhancement, Proc. Eurospeech99, 1999, 2837–2840.
15. Raj, B., Reconstruction of Incomplete Spectrograms for Robust Speech Recognition, Ph.D. thesis, Carnegie Mellon University, Pittsburgh, PA, 2000.
16. Vizinho, A., Green, P., Cooke, M., and Josifovski, L., Missing data theory, spectral subtraction and signal-to-noise estimation for robust ASR: An integrated study, Proc. Eurospeech99, 1999, 2407–2410.
17. Seltzer, M., Automatic Detection of Corrupted Speech Features for Robust Speech Recognition, Master’s thesis, Carnegie Mellon University, Pittsburgh, PA, 2000.
18. Moreno, P.J., Speech Recognition in Noisy Environments, Ph.D. thesis, Carnegie Mellon University, Pittsburgh, PA, 1996.
19. Davis, S. and Mermelstein, P., Comparison of parametric representation for monosyllabic word recognition in continuously spoken sentences, IEEE Trans. on Acoustics, Speech, and Signal Proc., 28(4), 357–366, 1980.
20. Singh, R. et al., Speech in noisy environments: Robust automatic segmentation, feature extraction, and hypothesis combination, Proc. ICASSP2001, 2001, 273–276.
21. Hansen, J.H.L. et al., Robust speech recognition in noise: An evaluation using the SPINE corpus, Proc. Eurospeech2001, 2001, 905–908.
22. Fischer, A. and Stahl, V., Database and online adaptation for improved speech recognition in car environments, Proc. ICASSP99, 1999, pp. 445–449.
23. Kim, D.Y., Kim, N.S., and Un, C.K., Model-based approach for robust speech recognition in noisy environments with multiple noise sources, Proc. Eurospeech97, 1997, 1123–1126.
24. Gales, M.J.F., The generation and use of regression class trees for MLLR adaptation, Tech. Rep. CUED/F-INFENG/TR.263, Cambridge University, Cambridge, U.K., 1996.
25. Chesta, C., Siohan, O., and Lee, C.-H., Maximum a posteriori linear regression for hidden Markov model adaptation, Proc. Eurospeech99, 1999, pp. 211–214.
26. Doh, S.-J., Enhancements to Transformation-Based Speaker Adaptation: Principal Component and Inter-Class Maximum Likelihood Linear Regression, Ph.D. thesis, Carnegie Mellon University, Pittsburgh, PA, 2000.