Summary
Any mismatch between training and test conditions can cause difficulty for current automatic speech recognition systems. In recent years many approaches have been proposed for resolving this mismatch problem. These approaches can be divided broadly into three classes: model adaptation, channel adaptation and robust features. This paper presents a review and discussion of methods for channel adaptation and their relationship to methods in the other classes.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
A.Acero and R.M.Stern. Environmental robustness in automatic speech recognition. In Proc. IEEE ICASSP, volume II, pages 849–852, 1990
Y. Cohen, A. Erell, and Y. Bistritz. Enhancement of connected words in an extremely noisy environment. IEEE Trans Speech and Audio Processing, 5 (2):141–148, March 1997
D.V.Compernolle. Improved noise immunity in large vocabulary speech recognition with the aid of spectral subtraction. In Proc.IEEE ICASSP, pages 1143–1146, Dallas, 1987
S.J.Cox and J.S. Bridle. Unsupervised speaker adaptation by probabilistic spectrum fitting. In Proc.IEEE ICASSP, pages 294–297, Glasgow, 1989
J.de Veth and L.Boves. Comparison of channel normalisation techniques for automatic speech recognition over the phone. In Proc. ICSLP, Philadelphia, 1996
Y.Ephraim.A minimum mean square error approach for speech enhancement. In Proc. IEEE ICASSP, pages 829–832, Albuquerque, 1990
Y.Ephraim.Statistical-model-based speech enhancement systems Proc. IEEE, 80: 1562–1555, 1992
A.Erell and M.Weintraub. Estimation using log-spectral-distance criterion for robust speech recognition. In Proc. IEEE ICASSP, pages 853–856, Albuquerque, 1990
A.Erell and M.Weintraub. Energy conditioned spectral estimation for recognition of noisy speech IEEE Trans Speech and Audio Processing 1(1), 1993
S.Furui.Cepstral analysis technique for automatic speaker verification. IEEE Trans Acoustics, Speech and Signal Processing, 29 (2): 254–272, April 1981
M.J.F. “Nice” model-based compensation schemes for robust speech recognition. In Robust Speech Recognition for Unknown Communication Channels, pages 55–64, Pont-a-Mousson, France, April 1997
B.A. Hanson and T.H.Applebaum.Robust speaker-independent word recognition using static, dynamic and acceleration features: Experiments with lombard and noisy speech. In Proc. IEEE ICASSP, volume II, pages 857–860, Albuquerque, 1990
H.Hermansky and N.Morgan. Rasta processing of speech IEEE Trans Speech and Audio Processing, 2 (4): 578–589, October 1994
H.G.Hirsch and C.Ehrlicher. Noise estimation techniques for robust speech recognition.In Proc. IEEE ICASSP, volume I, pages 153–156, Detroit, 1995
M.J. Hunt and S.M. Richardson. An investigation of PLP and IMELDA acoustic representations and of their potential combination.In Proc. IEEE ICASSP, volume 2, pages 881–884. IEEE, 1991
J.-C.Junqua. The Lombard reflex and its role on human listeners and automatic speech recognisers J. Acoust. Soc. Am, 93 (1): 510–524, 1993
C.J. Legetter and P.C. Woodland. Speaker adaption of HMMs using linear regression.Technical Report CUED/F-INFENG/TR181, Cambridge University Engineering Department, 1994
B.P. Milner and S.V. Vaseghi. Comparison of some noise compensation methods for speech recognition in adverse environments. Proc. IEE, 141: 280–288, 1994
S.Moon and J.-N.Hwang. Noisy speech recognition using robust inversion of hidden Markov models. In Proc. IEEE ICASSP, pages 145–148, Detroit, 1995
R.K.Moore. Signal decomposition using Markov modelling techniques. RSRE Memo 3931, DERA Malvern, St.Andrew’s Road, Great Malvern, Worcs. WR14 3PS, UK, 1986
P.J. Moreno, B. Raj, E.Gouvêa, and R. M. Stem. Multivariate gaussian based cepstral normalisation for robust speech recognition. In Proc.IEEE ICASSP, pages 137–140, Detroit, 1995
P.J.Moreno, B.Raj, and R.M.Stern. A vector Taylor series approach for environment-independent speech recognition. In Proc. IEEE ICASSP, volume II, pages 733–736, Atlanta, 1996
L.Neumeyer and M.Weintraub. Probabilistic optimum filtering for robust speech recognition. In Proc. IEEE ICASSP, pages 417–420, Adelaide, 1994
K.M.Ponting. Automatic speech recognition for time-varying channels. In Robust Speech Recognition for Unknown Communication Channels, pages 175–178, Pont-a-Mousson, France, April 1997
J.E.Porter and S.F.Boll. Optimal estimators for spectral restoration of noisy speech. In Proc. IEEE ICASSP, page 18A2.1, San Diego, 1984
M. G.Rahim and B.-H. Juang. Signal bias removal for robust telephone based speech recognition in adverse environments. In Proc. IEEE ICASSP volume I, pages 445–448, Adelaide, 1994. IEEE
M.G.Rahim, B.-H.Juang, W.Chou, and E.Buhrke. Signal conditioning techniques for robust speech recognition. IEEE Signal Processing Letters, 3 (4): 107–109, April 1996
B.Raj, E.B.Gouvea, P.J.Moreno, and R.M.Stern. Cepstral compensation by polynomial approximation for environment-independent speech recognition. In Proc. ICSLP, Philadelphia, 1996
A.Sankar and C.-H. Lee. Robust speech recognition based on stochastic matching. In Proc. IEEE ICASSP, pages 121–124, Detroit, 1995
A.Sankar and C.-H.Lee. A maximum likelihood approach to stochastic matching for robust speech recognition. IEEE Trans Speech and Audio Processing, 4 (3): 190–202, May 1996
R.M.Stern, B.Raj, and P.J.Moreno. Compensation for environmental degradation in automatic speech recognition. In Robust Speech Recognition for Unknown Communication Channels, pages 33–41, Pont-a-Mousson, France, April 1997
D. van Compernolle. Noise adaptation in a hidden Markov model speech recognition system. Computer Speech and Language, 3(2): 151–167, April 1989
A.P.Varga and R.K.Moore. Hidden Markov model decomposition of speech and noise. In Proc. IEEE ICASSP pages 845–848, Albuquerque, 1990.IEEE.
P. C. Woodland, M. J. F. Gales, and D. Pye. Improving environmental robustness in large vocabulary speech recognition. In Proc.IEEE ICASSP, volume 1, pages 65–68, Atlanta, 1996
F. Xie and D. V. Compernolle. Speech enhancement by spectral magnitude estimation -a unifying approach Speech Communication, 19(2): 89–104, 1996
Y. Zhao. An acoustic phonetic based speaker adaptation technique for improving continuous speaker independent speech recognition IEEE Trans Speech and Audio Processing, 2(3): 380–394, July 1994
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Ponting, K.M. (1999). Channel Adaptation. In: Ponting, K. (eds) Computational Models of Speech Pattern Processing. NATO ASI Series, vol 169. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-60087-6_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-60087-6_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-64250-0
Online ISBN: 978-3-642-60087-6
eBook Packages: Springer Book Archive