Voice source waveforms for utterance level speaker identification using support vector machines

David Vandyke, Michael Wagner, Roland Goecke

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

    7 Citations (Scopus)

    Abstract

    The voice source waveform generated by the periodic motion of the vocal folds during voiced speech remains to be fully utilised in automatic speaker recognition systems. We perform closed-set speaker identification experiments on the YOHO speech corpus with the aim of continuing our investigation into the level of speaker discriminatory information present in a data driven parameterisation of the voice-source waveform obtained by closed-phase inverse filtering. Discriminatory modelling using support-vector-machines resulted in utterance level correct identification rates of 85.3% when using a multi-class model, and 72.5% when using a binary, one-against-all regression model, each on cohorts of 20 speakers respectively. These results compare well with other speaker identification experiments in the literature employing features derived from the voice source waveform, and are positive when observed under the hypothesis that they should be complementary to the common magnitude spectral parameters (mel-cepstra).

    Original languageEnglish
    Title of host publication2013 8th International Conference on Information Technology in Asia - Smart Devices Trend
    Subtitle of host publicationTechnologising Future Lifestyle, Proceedings of CITA 2013
    PublisherIEEE Computer Society
    ISBN (Print)9781479910922
    DOIs
    Publication statusPublished - 2013
    Event2013 8th International Conference on Information Technology in Asia, CITA 2013 - Kota Samarahan, Malaysia
    Duration: 1 Jul 20134 Jul 2013

    Publication series

    Name2013 8th International Conference on Information Technology in Asia - Smart Devices Trend: Technologising Future Lifestyle, Proceedings of CITA 2013

    Conference

    Conference2013 8th International Conference on Information Technology in Asia, CITA 2013
    Country/TerritoryMalaysia
    CityKota Samarahan
    Period1/07/134/07/13

    Fingerprint

    Dive into the research topics of 'Voice source waveforms for utterance level speaker identification using support vector machines'. Together they form a unique fingerprint.

    Cite this