Agatha: Multimodal Biometric Authentication Platform in Large-Scale Databases



Biometric technologies are each time more demanded for security applications. In this sense, systems for identifying people are gaining popularity, especially in governmental sectors, and forensic applications have climbed to the top of the list when talking about biometrics. However, some problems still remain as cornerstones in identification processes, all of them linked to the length of the databases in which the individual is supposed to be. The speed and the error are parameters that depend on the number of users in the database and measure the quality of the whole system.

In this paper, two different biometric technologies are used in order to increase speed and shorten error rates. Face recognition -normally faster than speaker recognition — is used to select a group of individuals and speaker recognition provides a finer adjustment. Multimodality plays an important role not only reducing the search time but also providing lower error rates.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [Auckenthaler01]
    Auckenthaler R., Mason J.S.: Gaussian selection applied to text-independent speaker verification. In Proc. Speaker Odyssey: The Speaker Recognition Workshop (Odyssey 2001), Crete, Greece, 2001, pp.83–88.Google Scholar
  2. [Beigi99]
    Beigi H.S.M., Maes S.H., Sorensen J.S., Chaudhari U.V.: A hierarchical approach to large-scale speaker recognition. In Proc. 6th European Conf. Speech Communication and Technology (Eurospeech 1999). Budapest, 1999.Google Scholar
  3. [Bolle04]
    Bolle R. M., Connell J. H., Pankanti S., Ratha N. K., and Senior A. W.: Guide to Biometrics. Editor: Springer, New York. 2004.Google Scholar
  4. [Fox03]
    Fox N. A., Gross R., Chazal P., Cohn J. F., and Reilly R. B.: Person identification using automatic integration of speech, lip and face experts. In ACM SIGMM 2003 Multimedia Biometrics Methods and Applications Workshop, Berkeley, CA, 2003.Google Scholar
  5. [Kinnunen06]
    Kinnunen T., Karpov E., Fränti P.: Real-Time Speaker Identification and Verification. In IEEE Transactions on Audio, Speech, and Language Processing, vol. 14, no. 1, January 2006.Google Scholar
  6. [Indovina03]
    Indovina M., Uludag U., Snelik R., Mink A., and Jain A.: Multimodal Biometric Authentication Methods: A COTS Approach. In MMUA, Workshop on Multimodal User Authentication, Santa Barbara, CA, 2003.Google Scholar
  7. [Luettin98]
    Luettin J., Maitre G.: Evaluation protocol for the XM2FDB database (Lausanne protocol). In Communication 98-05, IDIAP, Martigny, Switzerland, 1998Google Scholar
  8. [McLaughin99]
    McLaughlin J., Reynolds D.A., Gleason T.: A study of computation speed-ups of the GMM-UBM speaker recognition system. In Proc. 6th European Conf. Speech Communication and Technology (Eurospeech 1999). Budapest, 1999.Google Scholar
  9. [Pellom98]
    Pellom B.L., Hansen J.H.L.: An efficient scoring algorithm for gaussian mixture model based speaker identification. In IEEE Signal Process. Lett. vol. 5, no 11, pp. 281–284, 1998CrossRefGoogle Scholar
  10. [Reynolds95]
    Reynolds D.A., Rose R.C.: Robust text-independent speaker identification using gaussian mixture speaker models. In IEEE Trans. Speech Audio Process., vol. 3, no. 1, pp. 72–83. 1995.CrossRefGoogle Scholar
  11. [Saeta06]
    Saeta J.R., Hernando J.: Weighting scores to improve speaker-dependent threshold estimation in text-dependent speaker verification. In Lecture Notes in Computer Science. Editor: Springer-Verlag, vol. 3817, 2006, pp. 81–91.CrossRefGoogle Scholar
  12. [Sun03]
    Sun B., Liu W., Zhong Q.: Hierarchical speaker identification using speaker clustering. In Proc. Int. Conf. Natural Language Processing and Knowledge Engineering 2003, Beijin, China, 2003, pp. 299–304.Google Scholar

Copyright information

© Vieweg+Teubner | GWV Fachverlage GmbH, Wiesbaden 2009

Authors and Affiliations

  1. 1.Biometric Technologies S.L.BarcelonaSpain
  2. 2.TALP Research CenterUniversitat Politècnica de CatalunyaSpain

Personalised recommendations