Gaussian Mixture Models for CHASM Signature Verification
In this paper we report on first experimental results of a novel multimodal user authentication system based on a combined acquisition of online handwritten signature and speech modalities. In our project, the so-called CHASM signatures are recorded by asking the user to utter what he is writing. CHASM actually stands for Combined Handwriting and Speech Modalities where the pen and voice signals are simultaneously recorded. We have built a baseline CHASM signature verification system for which we have conducted a complete experimental evaluation. This baseline system is composed of two Gaussian Mixture Models sub-systems that model independently the pen and voice signal. A simple fusion of both sub-systems is performed at the score level. The evaluation of the verification system is conducted on CHASM signatures taken from the MyIDea multimodal database, accordingly to the protocols provided with the database. This allows us to draw our first conclusions in regards to time variability impact, to skilled versus unskilled forgeries attacks and to some training parameters. Results are also reported for the two sub-systems evaluated separately and for the global system.
KeywordsGaussian Mixture Model Dynamic Time Warping Time Variability Equal Error Rate Universal Background Model
Unable to display preview. Download preview PDF.
- 2.Dumas, B., et al.: Myidea - multimodal biometrics database, description of acquisition protocols. In: Proc. of Third COST 275 Workshop (COST 275), Hatfield, UK, October 27-28, pp. 59–62 (2005)Google Scholar
- 3.Fuentes, M., et al.: Identity verification by fusion of biometric data: On-line signature and speech. In: Proc. COST 275 Workshop on The Advent of Biometrics on the Internet, Rome, Italy, November 2002, pp. 83–86 (2002)Google Scholar
- 5.Hennebert, J., Dumas, B., Pugin, C., Evéquoz, F., Humm, A., Petrovska-Delacrétaz, D.: MyIDea home page (2005), http://diuf.unifr.ch/go/myidea
- 6.Humm, A., Hennebert, J., Ingold, R.: Combined handwriting and speech modalities for user authentication. Technical Report 06-05, University of Fribourg, Department of Informatics (2006)Google Scholar
- 11.Ly-Van, B., Blouet, R., Renouard, S., Garcia-Salicetti, S., Dorizzi, B., Chollet, G.: Signature with text-dependent and text-independent speech for robust identity verification. In: Proc. MMUA, pp. 13–18 (December 2003)Google Scholar
- 12.Ly Van, B., Garcia-Salicetti, S., Dorizzi, B.: Fusion of hmm’s likelihood and viterbi path for on-line signature verification. In: Biometrics Authentication Workshop, Prague, May 15 (2004)Google Scholar
- 13.Martin, A., Doddington, G., Kamm, T., Ordowski, M., Przybocki, M.: The det curve in assesment of detection task performance. In: Eurospeech 1997, Rhodes, Greece, pp. 1895–1898 (1997)Google Scholar
- 14.Rabiner, L., Juang, B.-H.: Fundamentals Of Speech Recognition. Prentice-Hall, Englewood Cliffs (1993)Google Scholar
- 15.Reynolds, D.: Automatic speaker recognition using gaussian mixture speaker models. The Lincoln Laboratory Journal 8(2), 173–191 (1995)Google Scholar
- 16.Reynolds, D.: An overview of automatic speaker recognition technology. In: Proc. IEEE ICASSP, vol. 4, pp. 4072–4075 (2002)Google Scholar
- 17.Richiardi, J., Drygajlo, A.: Gaussian mixture models for on-line signature verification. In: Proc. 2003 ACM SIGMM workshop on Biometrics methods and applications, pp. 115–122 (2003)Google Scholar
- 18.Vielhauer, C.: Biometric User Authentication for IT Security. Springer, Heidelberg (2006)Google Scholar