A deep neural network for audio-visual person recognition

M.R. Alam, Mohammed Bennamoun, Roberto Togneri, Ferdous Sohel

    Research output: Chapter in Book/Conference paperConference paperpeer-review

    9 Citations (Scopus)

    Abstract

    © 2015 IEEE. This paper presents applications of special types of deep neural networks (DNNs) for audio-visual biometrics. A common example is the DBN-DNN that uses the generative weights of deep belief networks (DBNs) to initialize the feature detecting layers of deterministic feed forward DNNs. In this paper, we propose the DBM-DNN that uses the generative weights of deep Boltzmann machines (DBMs) for initialization of DNNs. Then, a softmax layer is added on top and the DNNs are trained discriminatively. Our experimental results show that lower error rates can be achieved using the DBM-DNN compared to the support vector machine (SVM), linear regression-based classifier (LRC) and the DBN-DNN. Experiments were carried out on two publicly available audio-visual datasets: the VidTIMIT and MOBIO.
    Original languageEnglish
    Title of host publicationBiometrics Theory, Applications and Systems (BTAS), 2015 IEEE 7th International Conference
    Place of PublicationUSA
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages1-6
    VolumeN/A
    ISBN (Print)9781479987764
    DOIs
    Publication statusPublished - 2015
    EventBiometrics Theory, Applications and Systems (BTAS) 2015 - Virginia, United States
    Duration: 8 Sept 201511 Sept 2015

    Conference

    ConferenceBiometrics Theory, Applications and Systems (BTAS) 2015
    Country/TerritoryUnited States
    CityVirginia
    Period8/09/1511/09/15

    Fingerprint

    Dive into the research topics of 'A deep neural network for audio-visual person recognition'. Together they form a unique fingerprint.

    Cite this