Low-Complexity Automatic Speaker Recognition in the Compressed GSM-AMR Domain

Item Type: Proceeding
MIUR type: Proceedings > Proceedings
Title: Low-Complexity Automatic Speaker Recognition in the Compressed GSM-AMR Domain
Authors string: M. Petracca; A. Servetti; De Martin J.C.
University authors:
Page Range: pp. 662-665
Publisher: IEEE
ISBN: 0780393317
Event Title: IEEE International Conference on Multimedia & Expo (ICME)
Event Location: Amsterdam, The Netherlands
Event Dates: 6-8 July 2005
Place of Publication: AMSTERDAM
Abstract: This paper presents an experimental implementation of a low-complexity speaker recognition algorithm working in the compressed speech domain. The goal is to perform speaker modeling and identication without decoding the speech bitstream to extract speaker dependent features, thus saving important system resources, for instance, in mobile devices. The compressed bitstream values of the widely used GSM AMR speech coding standard are studied to identify statistics enabling fair recognition after a few seconds of speech. Using euclidean distance measures on elementary statistical values such as coefficient of variation and skewness of nine standard GSM AMR parameters delivers recognition accuracies close to 100% after about 20 seconds of active speech for a database of 14 speakers recorded in a normal room environment
Date: 2005
Status: Published
Language of publication:
Uncontrolled Keywords:
Departments (original): DAUIN - Control and Computer Engineering
Departments: DAUIN - Department of Control and Computer Engineering
Related URLs:
    Subjects: Area 09 - Ingegneria industriale e dell'informazione > SISTEMI DI ELABORAZIONE DELLE INFORMAZIONI
    Date Deposited: 05 Oct 2006 14:10
    Last Modified: 16 Oct 2013 01:43
    Id Number (DOI): 10.1109/ICME.2005.1521510
    Permalink: http://porto.polito.it/id/eprint/1410962
    Linksolver URL: Linksolver link
    Citations:

    This field presents the citations number present on Scopus and Web of Science databases e links to the remote records. Also Google Scholar link is present.

    There may be discrepancies with respect to the data in databases for the following reasons:

    • Differences from fields (title, year,...) in UGOV and those in the databases.
    • PORTO citations are extracted monthly. The db is in real time
    • The WoS citation number reflect the collections subscribed by Politecnico (Science citation index Expanded and Conference Proceedings Citation Index)

    For informations contact scrivia/porto

    +
    -

    Documents

    [img] PDF (Low_Complexity_Automatic_Speaker_Recognition_in_the_Compressed_GSM_AMR_Domain) - Postprint
    Document access: Not visible (accessible only to the record owner)
    Licence: Not public - Private access / Restricted.

    Download (396Kb) | Send a request to the author for a copy of the paper
    [img] PDF (Best_Paper_Award) - Other
    Document access: Not visible (accessible only to the record owner)
    Licence: Not public - Private access / Restricted.

    Download (11Kb) | Send a request to the author for a copy of the paper

    Actions (login required)

    View Item View Item