• Login
    JavaScript is disabled for your browser. Some features of this site may not work without it.
    Analysing the predictions of a CNN-based replay spoofing detection system 
    •   QMRO Home
    • School of Electronic Engineering and Computer Science
    • Electronic Engineering and Computer Science
    • Analysing the predictions of a CNN-based replay spoofing detection system
    •   QMRO Home
    • School of Electronic Engineering and Computer Science
    • Electronic Engineering and Computer Science
    • Analysing the predictions of a CNN-based replay spoofing detection system
    ‌
    ‌

    Browse

    All of QMROCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects
    ‌
    ‌

    Administrators only

    Login
    ‌
    ‌

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular Authors

    Analysing the predictions of a CNN-based replay spoofing detection system

    View/Open
    Accepted version (224.4Kb)
    Pagination
    92 - 97
    Publisher
    IEEE
    Metadata
    Show full item record
    Abstract
    Playing recorded speech samples of an enrolled speaker - "replay attack" - is a simple approach to bypass an automatic speaker verification (ASV) system. The vulnerability of ASV systems to such attacks has been acknowledged and studied, but there has been no research into what spoofing detection systems are actually learning to discriminate. In this paper, we analyse the local behaviour of a replay spoofing detection system based on convolutional neural networks (CNNs) adapted from a state-of-the-art CNN (LCNN-FFT) submitted at the ASVspoof 2017 challenge. We generate temporal and spectral explanations for predictions of the model using the SLIME algorithm. Our findings suggest that in most instances of spoofing the model is using information in the first 400 milliseconds of each audio instance to make the class prediction. Knowledge of the characteristics that spoofing detection systems are exploiting can help build less vulnerable ASV systems, other spoofing detection systems, as well as better evaluation databases.
    Authors
    CHETTRI, B; MISHRA, S; STURM, B; BENETOS, E; 2018 IEEE Workshop on Spoken Language Technology
    URI
    https://qmro.qmul.ac.uk/xmlui/handle/123456789/55093
    Collections
    • Electronic Engineering and Computer Science [2315]
    Copyright statements
    © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
    Twitter iconFollow QMUL on Twitter
    Twitter iconFollow QM Research
    Online on twitter
    Facebook iconLike us on Facebook
    • Site Map
    • Privacy and cookies
    • Disclaimer
    • Accessibility
    • Contacts
    • Intranet
    • Current students

    Modern Slavery Statement

    Queen Mary University of London
    Mile End Road
    London E1 4NS
    Tel: +44 (0)20 7882 5555

    © Queen Mary University of London.