In this article, we present a novel forensic speaker recognition system that provides the capability to perform comparisons using both ‘traditional’ forensic phonetic parameters and ‘automatic’ spectral features in a semi- or fully automatic way. We evaluate this approach with simulated and real forensic case data in German, which ranges from high quality laboratory audio data to real telephone intercepts. We examine how the forensic expert can use his or her knowledge of the linguistic and phonetic content of the speech and combine it with ‘automatic’ acoustic analysis of the speech. This approach is shown to provide a level of validation and safeguard against misleading or incorrect identification results. We demonstrate that processing phonetic data will be in many ways complementary and will offer insights into the voice comparison analysis that the classical automatic methods cannot.

Authors: Jesse, Michael; Alexander, Anil; Forth, Oscar
Affiliations: Department of Speaker Identification and Audio Analysis, Bundeskriminalamt, Germany; Oxford Wave Research Ltd., Oxford, UK(See document for exact affiliation information.)
AES Conference: 54th International Conference: Audio Forensics (June 2014)
Paper Number: 2-2
Publication Date: June 12, 2014 Import into BibTeX
Subject: Forensic Speaker Recognition
Permalink: https://www.aes.org/e-lib/browse.cfm?elib=17328

Click to purchase paper as a non-member or login as an AES member. If your company or school subscribes to the E-Library then switch to the institutional version. If you are not an AES member and would like to subscribe to the E-Library then Join the AES!

This paper costs $33 for non-members and is free for AES members and E-Library subscribers.

Learn more about the AES E-Library

E-Library Location: (CD 54thPapers)   /conf/54/aes54-000035.pdf

Start a discussion about this paper!