Likelihood Ratio-based Forensic Voice Comparison on L2 speakers: A Case of Hong Kong native male production of English vowels
dc.contributor.author | Frost, Daniel | |
dc.contributor.author | Ishihara, Shunichi | |
dc.contributor.editor | Ben Hachey | |
dc.contributor.editor | Kellie Webster | |
dc.coverage.spatial | Western Sydney University, Parramatta | |
dc.date.accessioned | 2016-06-14T23:21:37Z | |
dc.date.created | 8-9 December 2015 | |
dc.date.issued | 2015 | |
dc.date.updated | 2021-08-01T08:41:08Z | |
dc.description.abstract | The performances of two different procedures for calculating the likelihood ratio (LR) for forensic text comparison (FTC) are empirically compared. One is the multivariate kernel density (MVKD) procedure with so-called lexical features. The MVKD procedure has been successfully applied to various types of evidence, including texts. The other is the procedure based on character N-grams. N-gram is a widely-used, robust probabilistic language model. The effectiveness of character N-grams has been reported in authorship analysis, however, to the best of my knowledge, it has not yet been applied to LR-based FTC. In this study, the log-likelihood-ratio-cost (Cllr), which is an appropriate assessment metric for LR-based systems, is used to assess the performance of the two procedures. It will be reported that the MVKD procedure outperforms the character N-gram procedure. Through the comparison of the two procedures, this study also demonstrates how the weight of evidence (= LR) can be estimated from text messages. | |
dc.identifier.isbn | 1834-7037 | |
dc.identifier.uri | http://hdl.handle.net/1885/104003 | |
dc.publisher | University of Western Sydney | |
dc.relation.ispartofseries | Australasian Language Technology Association Workshop 2015 | |
dc.rights | Author/s retain copyright | |
dc.source | Australasian Language Technology Association Workshop 2015 Proceedings of the Workshop | |
dc.source.uri | http://www.alta.asn.au/events/alta2015/proceedings.pdf | |
dc.title | Likelihood Ratio-based Forensic Voice Comparison on L2 speakers: A Case of Hong Kong native male production of English vowels | |
dc.type | Conference paper | |
dcterms.accessRights | Open Access | en_AU |
local.bibliographicCitation.lastpage | 47 | |
local.bibliographicCitation.startpage | 39 | |
local.contributor.affiliation | Frost, Daniel, College of Arts and Social Sciences, ANU | |
local.contributor.affiliation | Ishihara, Shunichi, College of Asia and the Pacific, ANU | |
local.contributor.authoremail | u9504440@anu.edu.au | |
local.contributor.authoruid | Frost, Daniel, u4406450 | |
local.contributor.authoruid | Ishihara, Shunichi, u9504440 | |
local.description.notes | Imported from ARIES | |
local.description.refereed | Yes | |
local.identifier.absfor | 200404 - Laboratory Phonetics and Speech Science | |
local.identifier.absfor | 200312 - Japanese Language | |
local.identifier.absseo | 940403 - Criminal Justice | |
local.identifier.absseo | 970110 - Expanding Knowledge in Technology | |
local.identifier.absseo | 940406 - Legal Processes | |
local.identifier.ariespublication | u5567033xPUB50 | |
local.identifier.uidSubmittedBy | u5567033 | |
local.type.status | Published Version |
Downloads
Original bundle
1 - 1 of 1
Loading...
- Name:
- 01_Frost_Likelihood_Ratio-based_2015.pdf
- Size:
- 1.98 MB
- Format:
- Adobe Portable Document Format