Results 1 
2 of
2
Bayesian calibration for forensic evidence reporting
"... We introduce a Bayesian solution for the problem in forensic speaker recognition, where there may be very little background material for estimating score calibration parameters. We work within the Bayesian paradigm of evidence reporting and develop a principled probabilistic treatment of the proble ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
We introduce a Bayesian solution for the problem in forensic speaker recognition, where there may be very little background material for estimating score calibration parameters. We work within the Bayesian paradigm of evidence reporting and develop a principled probabilistic treatment of the problem, which results in a Bayesian likelihoodratio as the vehicle for reporting weight of evidence. We show in contrast, that reporting a likelihoodratio distribution does not solve this problem. Our solution is experimentally exercised on a simulated forensic scenario, using NIST SRE’12 scores, which demonstrates a clear advantage for the proposed method compared to the traditional plugin calibration recipe. Index Terms: forensic speaker recognition, Bayesian paradigm 1.
CALCULATION OF FORENSIC LIKELIHOOD RATIOS: USE OF MONTE CARLO SIMULATIONS TO COMPARE THE OUTPUT OF SCORE BASED APPROACHES WITH TRUE LIKELIHOODRATIO VALUES
, 2015
"... A group of approaches for calculating forensic likelihood ratios first calculates scores which quantify the degree of difference or the degree of similarity between pairs of samples, then converts those scores to likelihood ratios. In order for a scorebased approach to produce a forensically interp ..."
Abstract
 Add to MetaCart
A group of approaches for calculating forensic likelihood ratios first calculates scores which quantify the degree of difference or the degree of similarity between pairs of samples, then converts those scores to likelihood ratios. In order for a scorebased approach to produce a forensically interpretable likelihood ratio, however, in addition to accounting for the similarity of the questioned sample with respect to the known sample, it must also account for the typicality of the questioned sample with respect to the relevant population. The present paper explores a number of scorebased approaches using different types of scores and different procedures for converting scores to likelihood ratios. Monte Carlo simulations are used to compare the output of these approaches to true likelihoodratio values calculated on the basis of the distribution specified for a simulated population. The inadequacy of approaches based on similarityonly or differenceonly scores is illustrated, and the relative performance of different approaches which take account of both similarity and typicality is assessed.