Publication detail

Fusing linguistic and acoustic information for automated forensic speaker comparison

SERGIDOU, E. YPMA, R. ROHDIN, J. WORRING, M. GERADTS, Z. BOSMA, W.

Original Title

Type

journal article in Web of Science

Language

English

Original Abstract

Verifying the speaker of a speech fragment can be crucial in attributing a crime to a suspect. The question can be addressed given disputed and reference speech material, adopting the recommended and scientifically accepted likelihood ratio framework for reporting evidential strength in court. In forensic practice, usually, auditory and acoustic analyses are performed to carry out such a verification task considering a diversity of features, such as language competence, pronunciation, or other linguistic features. Automated speaker comparison systems can also be used alongside those manual analyses. State-of-the-art automatic speaker comparison systems are based on deep neural networks that take acoustic features as input. Additional information, though, may be obtained from linguistic analysis. In this paper, we aim to answer if, when and how modern acoustic-based systems can be complemented by an authorship technique based on frequent words, within the likelihood ratio framework. We consider three different approaches to derive a combined likelihood ratio: using a support vector machine algorithm, fitting bivariate normal distributions, and passing the score of the acoustic system as additional input to the frequent-word analysis. We apply our method to the forensically relevant dataset FRIDA and the FISHER corpus, and we explore under which conditions fusion is valuable. We evaluate our results in terms of log likelihood ratio cost (Cllr) and equal error rate (EER). We show that fusion can be beneficial, especially in the case of intercepted phone calls with noise in the background.

Keywords

Forensic speaker comparison; Frequent-word analysis; Likelihood ratio framework; Multi-modal analysis; Information fusion

Authors

SERGIDOU, E.; YPMA, R.; ROHDIN, J.; WORRING, M.; GERADTS, Z.; BOSMA, W.

Released

1. 9. 2024

Publisher

ELSEVIER SCI LTD

Location

London

ISBN

1355-0306

Periodical

SCIENCE & JUSTICE

Year of study

Number

State

United Kingdom of Great Britain and Northern Ireland

Pages from

485

Pages to

497

Pages count

URL

https://pdf.sciencedirectassets.com/274162/1-s2.0-S1355030624X00040/1-s2.0-S135503062400056X/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEJj%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FwEaCXVzLWVhc3QtMSJIMEYCIQD8rjrZi%2FhPcL5bX04sCPiZ7t1gOY2P2HhckbMwnNI%2BowIhAPSL1qk91pZeBYKl64ulkkxTVtGNw3%2FhcIqIe%2FEsECyAKrIFCBAQBRoMMDU5MDAzNTQ2ODY1IgxJGUcIfesue7uRz0EqjwUbwoISPHhLCgSSGV1GRJPKCbpWqK%2FjTNoJ8dlrM8OaDty8YcGiIu6bGFuunKMWP8xvOPfBMwuBvUFIGCkck2SA1BZ3bw6jWH8Yw%2Bi5jxtOK3MUMpsz5jwX8iDTWAhPR2ZNsKsAQiR9dL%2Bw3BCfgX8UOh5Y6S66bfh

BibTex

@article{BUT197614,
  author="Eleni Konstantina {Sergidou} and Rolf {Ypma} and Johan Andréas {Rohdin} and Marcel {Worring} and Zeno {Geradts} and Wauter {Bosma}",
  title="Fusing linguistic and acoustic information for automated forensic speaker comparison",
  journal="SCIENCE & JUSTICE",
  year="2024",
  volume="64",
  number="5",
  pages="485--497",
  doi="10.1016/j.scijus.2024.07.001",
  issn="1355-0306",
  url="https://pdf.sciencedirectassets.com/274162/1-s2.0-S1355030624X00040/1-s2.0-S135503062400056X/main.pdf?X-Amz-Security-Token=IQoJb3JpZ2luX2VjEJj%2F%2F%2F%2F%2F%2F%2F%2F%2F%2FwEaCXVzLWVhc3QtMSJIMEYCIQD8rjrZi%2FhPcL5bX04sCPiZ7t1gOY2P2HhckbMwnNI%2BowIhAPSL1qk91pZeBYKl64ulkkxTVtGNw3%2FhcIqIe%2FEsECyAKrIFCBAQBRoMMDU5MDAzNTQ2ODY1IgxJGUcIfesue7uRz0EqjwUbwoISPHhLCgSSGV1GRJPKCbpWqK%2FjTNoJ8dlrM8OaDty8YcGiIu6bGFuunKMWP8xvOPfBMwuBvUFIGCkck2SA1BZ3bw6jWH8Yw%2Bi5jxtOK3MUMpsz5jwX8iDTWAhPR2ZNsKsAQiR9dL%2Bw3BCfgX8UOh5Y6S66bfh"
}