Background population: how does it affect LR based forensic voice comparison?

Authors

  • Yuko Kinoshita The Australian National University
  • Shunichi Ishihara The Australian National University

DOI:

https://doi.org/10.1558/ijsll.v21i2.191

Keywords:

forensic voice comparison, background population, long term F0 distribution, likelihood ratio, spontaneous speech, Japanese

Abstract

This article investigates to what extent and in what ways the size of the background population affects the outcome of likelihood ratio (LR) based forensic voice comparison. While sample size is known to affect the accuracy of statistical modelling, specific effects in the context of forensic voice comparison are not yet understood. Forensic voice comparison analysts need to work with limited data, but it is unclear how this might impact on the LR-based evaluation of evidence. In this article, we report LR-based speaker comparison experiments using variously sized datasets for background population. They use features derived from long term F0 distribution. We examined their performance in terms of accuracy (closeness to the true value) and precision (reproducibility).

Author Biographies

  • Yuko Kinoshita, The Australian National University
    Dr Yuko Kinoshita is a research associate at the Australian National University. Yuko’s research interests include forensic voice comparison, acoustic phonetics, and foreign language education. She also works as a consultant in forensic speech analysis, and has performed casework analysis for a number of law enforcement agencies. She is a member of the Forensic Speech Science Committee of the Australian Speech Science and Technology since 2004.
  • Shunichi Ishihara, The Australian National University
    Shunichi Ishihara is a senior lecturer at the Department of Linguistics of the Australian National University. He is a speech scientist and a computational linguist with his main interest in forensic voice/text comparison, individual/gender differences manifested in language use and speech & language processing. He is an executive member of the Australasian Speech Science and Technology Association (ASSTA). He is also a member of the ASSTA's Forensic Speech Science Committee.

Downloads

Additional Files

Published

2015-02-18

Issue

Vol. 21 No. 2 (2014)

Section

Articles

License

© Equinox Publishing Ltd.

For information regarding our Open Access policy, click here.

How to Cite

Kinoshita, Y., & Ishihara, S. (2015). Background population: how does it affect LR based forensic voice comparison?. International Journal of Speech, Language and the Law, 21(2), 191-224. https://doi.org/10.1558/ijsll.v21i2.191