Speech-based Annotation of Heterogeneous Multimedia Content Using Automatic Speech Recognition

    Research output: Book/ReportReportProfessional

    35 Downloads (Pure)

    Abstract

    This paper reports on the setup and evaluation of robust speech recognition system parts, geared towards transcript generation for heterogeneous, real-life media collections. The system is deployed for generating speech transcripts for the NIST/TRECVID-2007 test collection, part of a Dutch real-life archive of news-related genres. Performance figures for this type of content are compared to figures for broadcast news test data.
    Original languageUndefined
    Place of PublicationEnschede
    PublisherCentre for Telematics and Information Technology (CTIT)
    Number of pages11
    Publication statusPublished - 9 May 2007

    Publication series

    NameCTIT Technical Report Series
    PublisherUniversity of Twente, Centre for Telematics and Information Technology (CTIT)
    No.WP07-01/TR-CTIT-07-30
    ISSN (Print)1381-3625

    Keywords

    • HMI-SLT: Speech and Language Technology
    • EWI-9783
    • Information Retrieval
    • Automatic Speech Recognition
    • IR-95701
    • METIS-241618
    • HMI-MR: MULTIMEDIA RETRIEVAL

    Cite this

    Huijbregts, M. A. H., Ordelman, R. J. F., & de Jong, F. M. G. (2007). Speech-based Annotation of Heterogeneous Multimedia Content Using Automatic Speech Recognition. (CTIT Technical Report Series; No. WP07-01/TR-CTIT-07-30). Enschede: Centre for Telematics and Information Technology (CTIT).