Automatic-type calibration of traditionally derived likelihood ratios:Forensic analysis of Australian English /o/ formant trajectories

Abstract

A traditional-style phonetic-acoustic forensic-speaker-recognition analysis was conducted on Australian English /o/ recordings. Different parametric curves were fitted to the formant trajectories of the vowel tokens, and cross-validated likelihood ratios were calculated using a single-stage generative multivariate kernel density formula. The outputs of different systems were compared using C llr, a metric developed for automatic speaker recognition, and the cross-validated likelihood ratios were calibrated using a procedure developed for automatic speaker recognition. Calibration ameliorated some likelihood-ratio results which had offered strong support for a contrary-to-fact hypothesis.

Divisions: College of Business and Social Sciences > Aston Institute for Forensic Linguistics
College of Business and Social Sciences > School of Social Sciences & Humanities
Additional Information: Copyright © 2008 ISCA
Event Title: 9th Annual Conference of the International Speech Communication Association
Event Type: Other
Event Dates: 2008-09-22 - 2008-09-26
Uncontrolled Keywords: Calibration,Forensic speaker recognition,Formant trajectories,Human-Computer Interaction,Signal Processing,Software,Sensory Systems
Last Modified: 15 Jan 2024 08:42
Date Deposited: 14 Nov 2018 14:12
Full Text Link:
Related URLs: http://www.scop ... tnerID=8YFLogxK (Scopus URL)
https://www.isc ... 8/i08_1501.html (Publisher URL)
PURE Output Type: Conference contribution
Published Date: 2008
Authors: Morrison, Geoffrey Stewart (ORCID Profile 0000-0001-8608-8207)
Kinoshita, Yuko

Download

[img]

Version: Accepted Version

| Preview

Export / Share Citation


Statistics

Additional statistics for this record