The AMI speaker diarization system for NIST RT06s meeting data

David A. van Leeuwen, M.A.H. Huijbregts

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    35 Citations (Scopus)
    416 Downloads (Pure)

    Abstract

    We describe the systems submitted to the NIST RT06s evaluation for the Speech Activity Detection (SAD) and Speaker Diarization (SPKR) tasks. For speech activity detection, a new analysis methodology is presented that generalizes the Detection Erorr Tradeoff analysis commonly used in speaker detection tasks. The speaker diarization systems are based on the TNO and ICSI system submitted for RT05s. For the conference room evaluation Single Distant Microphone condition, the SAD results perform well at 4.23 % error rate, and the ‘HMM-BIC’ SPKR results perform competatively at an error rate of 37.2 % including overlapping speech.
    Original languageUndefined
    Title of host publicationNIST Rich Transcription 2006 Spring Meeting Recognition Evaluation, RT06s
    Place of PublicationBerlin
    PublisherSpringer
    Pages371-384
    Number of pages15
    ISBN (Print)978-3-540-69267-6
    DOIs
    Publication statusPublished - 10 Oct 2007
    EventNIST Rich Transcription 2006 Spring Meeting Recognition Evaluation, RT06s - Washington DC, USA
    Duration: 10 May 200611 May 2006

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer Verlag
    Number1
    Volume4299

    Workshop

    WorkshopNIST Rich Transcription 2006 Spring Meeting Recognition Evaluation, RT06s
    Period10/05/0611/05/06
    Other10-11 May 2006

    Keywords

    • EWI-8483
    • METIS-241856
    • EC Grant Agreement nr.: FP6/506811
    • IR-66707

    Cite this