Abstract
In this paper we propose the inversion of nonlinear distortions in order to improve the recognition rates of a speaker recognizer system. We study the effect of saturations on the test signals, trying to take into account real situations where the training material has been recorded in a controlled situation but the testing signals present some mismatch with the input signal level (saturations). The experimental results for speaker recognition shows that a combination of several strategies can improve the recognition rates with saturated test sentences from 80% to 89.39%, while the results with clean speech (without saturation) is 87.76% for one microphone, and for speaker identification can reduce the minimum detection cost function with saturated test sentences from 6.42% to 4.15%, while the results with clean speech (without saturation) is 5.74% for one microphone and 7.02% for the other one.
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
Prakriya, S., Hatzinakos, D.: Blind identification of LTI-ZMNL-LTI nonlinear channel models. Biol. Cybern. 55, 135–144 (1985)
Bellings, S.A., Fakhouri, S.Y.: Identification of a class of nonlinear systems using correlation analysis. Proc. IEEE 66, 691–697 (1978)
Nikias, C.L., Petropulu, A.P.: Higher-Order Spectra Analysis – A Nonlinear Signal processing Framework. Prentice-Hall, Englewood Cliffs (1993)
Nikias, C.L., Raghuveer, M.R.: Bispectrum estimation: A digital signal processing framework. Proc. IEEE 75, 869–890 (1987)
Boer, E.D.: Cross-correlation function of a bandpass nonlinear network. Proc. IEEE 64, 1443–1444 (1976)
Jacoviti, G., Neri, A., Cusani, R.: Methods for estimating the autocorrelation function of complex stationary process. IEEE Trans. ASSP 35, 1126–1138 (1987)
Solé, J., Jutten, C., Taleb, A.: Parametric approach to blind deconvolution of nonlinear channels. Neurocomputing 48, 339–355 (2002)
Taleb, A., Jutten, C.: Source separation in postnonlinear mixtures. IEEE Trans. on S.P. 47(10), 2807–2820 (1999)
Taleb, A., Solé, J., Jutten, C.: Quasy-Nonparametric Blind Inversion of Wiener Systems. IEEE Trans. on S.P. 49(5), 917–924 (2001)
Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley Series in Telecommunications (1991)
Satué, A., Faúndez-Zanuy, M.: On the relevance of language in speaker recognition. In: EUROSPEECH 1999 Budapest, vol. 3, pp. 1231–1234 (1999)
Alonso, C., Faúndez-Zanuy, M.: Speaker identification in mismatch training and testing conditions. In: IEEE ICASSP 2000, Istanbul, vol. II, pp. 1181–1184 (2000)
Ortega, J., Gonzalez, J., Marrero, V.: Ahumada: a large speech corpus in spanish for speaker characterization and identification. Speech Communication 31, 255–264 (2000)
Bimbot, F., Mathan, L.: Text-free speaker recognition using an arithmetic-harmonic sphericity measure. In: Eurospeech 1993, pp. 169–172 (1993)
Martin, A., Doddington, G., Kamm, T., Ordowski, M., Przybocki, M.: The DET curve in assessment of detection performance. In: Eurospeech 1997, vol. 4, pp. 1895–1898 (1997)
Faundez-Zanuy, M.: Data fusion in biometrics. IEEE Aerospace and Electronic Systems Magazine (2004) (in press)
Kittler, J., Hatef, M., Duin, R.P.W., Matas, J.: On combining classifiers. IEEE Trans. On pattern analysis and machine intelligence 20(3), 226–239 (1998)
Sanderson: Information fusion and person verification using speech & face information. IDIAP Research Report 02-33, pp. 1–37 (September 2002)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Solé-Casals, J., Faúndez-Zanuy, M. (2004). Application of the Mutual Information Minimization to Speaker Recognition / Verification Improvement. In: Puntonet, C.G., Prieto, A. (eds) Independent Component Analysis and Blind Signal Separation. ICA 2004. Lecture Notes in Computer Science, vol 3195. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30110-3_109
Download citation
DOI: https://doi.org/10.1007/978-3-540-30110-3_109
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23056-4
Online ISBN: 978-3-540-30110-3
eBook Packages: Springer Book Archive