Adapted Gaussian mixture model in likelihood ratio based forensic voice comparison using long term fundamental frequency

Carolin Buncle Diesner, Shunichi Ishihara

    Research output: Contribution to conferencePaper

    Abstract

    In this paper, the Gaussian Mixture Model – Universal Background Model (GMM-UBM) is applied to onedimensional speech data, namely the distribution of long term fundamental frequency (LTF0) in likelihood ratio based forensic voice comparison. A series of experiments were conducted using varying numbers of Gaussians, differing adaptation rates to a UBM, and different lengths of speech samples. The results of the GMM-UBM procedure are compared to two previously proposed procedures for LTF0. All three procedures exhibited unique characteristics in their performances. Thus, there was no consistency in performance in that no one procedure constantly outperformed the others. Index Terms: forensic voice comparison, likelihood ratio, GMM-UBM, long-term F0 distribution
    Original languageEnglish
    Pages141-144pp
    Publication statusPublished - 2016
    EventSixteenth Australasian International Conference on Speech Science and Technology - Parramatta, Australia
    Duration: 1 Jan 2016 → …

    Conference

    ConferenceSixteenth Australasian International Conference on Speech Science and Technology
    Period1/01/16 → …

    Fingerprint Dive into the research topics of 'Adapted Gaussian mixture model in likelihood ratio based forensic voice comparison using long term fundamental frequency'. Together they form a unique fingerprint.

    Cite this