Faculté des sciences
Texte intégral

Distributed speaker recognition using the ETSI Aurora standard

Grassi, Sara ; Ansorge, Michael ; Pellandini, Fausto ; Farine, Pierre-André

In: Proceedings of the 3rd COST 276 Workshop on Information and Knowledge Management for Integrated Media Communication, 2002, vol. 276, no. 3, p. 120-125

The ETSI “Aurora” is a standard for distributed speech recognition over the mobile cellular network. We have investigated the use of the features defined in this standard for speaker recognition, in a text-independent system based on Gaussian Mixture Models (GMM). The application context is distributed speaker recognition for user authentication on the mobile cellular network.... More

Add to personal list
    Title
    • Distributed speaker recognition using the ETSI Aurora standard
    Author
    • Grassi, Sara. Institut de Microtechnique, Université de Neuchâtel, Switzerland
    • Ansorge, Michael. Institut de Microtechnique, Université de Neuchâtel, Switzerland
    • Pellandini, Fausto. Institut de Microtechnique, Université de Neuchâtel, Switzerland
    • Farine, Pierre-André. Institut de Microtechnique, Université de Neuchâtel, Switzerland
    Document Type
    • Postprint
    Publication Date
    • 2002-10-11
    Language
    • English
    Published in
    • Proceedings of the 3rd COST 276 Workshop on Information and Knowledge Management for Integrated Media Communication, 2002, vol. 276, no. 3, p. 120-125. COST (European Cooperation in the field of Scientific and Technical Research)
    Other Version
    OAI-PMH Identifier
    • oai:doc.rero.ch:20061129154722-TU
    Submission No.
    • 20061129154722-TU
    Summary
    The ETSI “Aurora” is a standard for distributed speech recognition over the mobile cellular network. We have investigated the use of the features defined in this standard for speaker recognition, in a text-independent system based on Gaussian Mixture Models (GMM). The application context is distributed speaker recognition for user authentication on the mobile cellular network. We have found that the use of the Aurora parameters would improve the performance compared with the existing alternative which is performing speaker recognition on GSM coded speech.