The Effect of the Within-speaker Sample Size on the Performance of Likelihood Ratio Based Forensic Voice Comparison: Monte Carlo Simulations

Shunichi Ishihara*

*Corresponding author for this work

    Research output: Contribution to conferencePaperpeer-review

    3 Citations (Scopus)

    Abstract

    This study is an investigation into the effect of sample size on a likelihood ratio (LR) based forensic voice comparison (FVC) system. In particular, we looked into how the offender and suspect sample size (or the within-speaker sample size) would affect the performance of the FVC system, using spectral feature vectors extracted from spontaneous Japanese speech. For this purpose, we repeatedly conducted Monte Carlo method based experiments with different sample size, using the statistics obtained from these feature vectors. LRs were estimated using the multivariate kernel density LR formula developed by Aitken and Lucy (2004). The derived LRs were calibrated using the logistic-regression calibration technique proposed by Brümmer and du Preez (2006). The performance of the FVC system was assessed in terms of the log-likelihood-ratio cost (Cllr) and the 95% credible interval (CI), which are the metrics of validity and reliability, respectively. We will demonstrate in this paper that 1) the validity of the system notably improves when up to six tokens are included in modelling a speaker session, and 2) the system performance converges with the relative small token number (four) in the background database, regardless of the token numbers in the test and development databases.

    Original languageEnglish
    Pages25-33
    Number of pages9
    Publication statusPublished - 2013
    Event2013 Australasian Language Technology Association Workshop, ALTA 2013 - Brisbane, Australia
    Duration: 4 Dec 20136 Dec 2013

    Conference

    Conference2013 Australasian Language Technology Association Workshop, ALTA 2013
    Country/TerritoryAustralia
    CityBrisbane
    Period4/12/136/12/13

    Fingerprint

    Dive into the research topics of 'The Effect of the Within-speaker Sample Size on the Performance of Likelihood Ratio Based Forensic Voice Comparison: Monte Carlo Simulations'. Together they form a unique fingerprint.

    Cite this