Front-end approaches to the issue of correlations in forensic speaker comparison

Erica Gold, Vincent Hughes

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


In likelihood ratio (LR)-based forensic speaker comparison it is essential to consider correlations between parameters to accurately estimate the overall strength of the evidence. Current approaches attempt to deal with correlations after the computation of LRs (back-end processing). This paper explores alternative, front-end techniques, which consider the underlying correlation structure of the raw data. Calibrated LRs were computed for a range of parameters commonly analysed in speaker comparisons. LRs were combined using (1) an assumption of independence, (2) the mean, (3) assumptions from phonetic theory, and (4) empirical correlations in the raw data. System (1), based on an assumption of independence, produced the best validity (Cllr = 0.04). Predictably, overall strength of evidence was also highest for system (1), while strength of evidence was weakest using the mean (2). Both systems (3) and (4) performed well achieving Cllr values of ca. 0.09.
Original languageEnglish
Title of host publicationProceedings of the 18th International Congress of Phonetic Sciences
Place of PublicationGlasgow, UK
PublisherUniversity of Glasgow
Number of pages5
ISBN (Electronic)9780852619414
Publication statusPublished - 2015
Event18th International Congress of Phonetic Sciences - Scottish Event Campus, Glasgow, United Kingdom
Duration: 10 Aug 201514 Aug 2015
Conference number: 18 (Link to Conference Details)


Conference18th International Congress of Phonetic Sciences
Abbreviated titleICPhS 2015
Country/TerritoryUnited Kingdom
Internet address


Dive into the research topics of 'Front-end approaches to the issue of correlations in forensic speaker comparison'. Together they form a unique fingerprint.

Cite this