The effect of speaker sampling in likelihood ratio based forensic voice comparison

IF 0.5 4区社会学 Q4 CRIMINOLOGY & PENOLOGY

International Journal of Speech Language and the Law Pub Date : 2019-08-23 DOI:10.1558/IJSLL.38046

B. Wang, Vincent Hughes, P. Foulkes

{"title":"The effect of speaker sampling in likelihood ratio based forensic voice comparison","authors":"B. Wang, Vincent Hughes, P. Foulkes","doi":"10.1558/IJSLL.38046","DOIUrl":null,"url":null,"abstract":"Within the field of forensic voice comparison (FVC), there is growing pressure for experts to demonstrate the validity and reliability of the conclusions they reach in casework. One benefit of a fully data-driven approach that utilises databases of speakers to compute numerical likelihood ratios (LRs) is that it is possible to estimate validity and reliability empirically. However, little is known about the stability of LR output as a function of the specific speakers sampled for use in the training, test and reference data sets. The present study addresses this issue using two large sets of formant data: Cantonese sentence final particle /a/ and British English filled pauses UM. Experiments were replicated 100 times varying the 1) training, test and reference speakers, 2) training speakers only, 3) test speakers only, and 4) reference speakers only. The results show that varying the speakers in all three sets has the greatest effect on system stability for both the Cantonese and English variables, with the Cllr varying from 0.60 to 0.97 for /a/ and 0.32 to 1.33 for UM. However, this variability is primarily due to the effects of uncertainty in the test set. Varying only the training speakers has the least effect on system stability for /a/ (Cllr range: 0.76 to 0.88), while varying reference speakers has the smallest effect for UM (Cllr range: 0.40 to 0.54). The results indicate that in LR-based FVC it is important to assess the stability of the system as a function of the samples of speakers used (Cllr range) rather than just reporting a single Cllr value based on one configuration of speakers in each set. The study contributes to the general debate on reporting uncertainty in LR computation.","PeriodicalId":43843,"journal":{"name":"International Journal of Speech Language and the Law","volume":" ","pages":""},"PeriodicalIF":0.5000,"publicationDate":"2019-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Speech Language and the Law","FirstCategoryId":"98","ListUrlMain":"https://doi.org/10.1558/IJSLL.38046","RegionNum":4,"RegionCategory":"社会学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"CRIMINOLOGY & PENOLOGY","Score":null,"Total":0}

引用次数: 11

Abstract

Within the field of forensic voice comparison (FVC), there is growing pressure for experts to demonstrate the validity and reliability of the conclusions they reach in casework. One benefit of a fully data-driven approach that utilises databases of speakers to compute numerical likelihood ratios (LRs) is that it is possible to estimate validity and reliability empirically. However, little is known about the stability of LR output as a function of the specific speakers sampled for use in the training, test and reference data sets. The present study addresses this issue using two large sets of formant data: Cantonese sentence final particle /a/ and British English filled pauses UM. Experiments were replicated 100 times varying the 1) training, test and reference speakers, 2) training speakers only, 3) test speakers only, and 4) reference speakers only. The results show that varying the speakers in all three sets has the greatest effect on system stability for both the Cantonese and English variables, with the Cllr varying from 0.60 to 0.97 for /a/ and 0.32 to 1.33 for UM. However, this variability is primarily due to the effects of uncertainty in the test set. Varying only the training speakers has the least effect on system stability for /a/ (Cllr range: 0.76 to 0.88), while varying reference speakers has the smallest effect for UM (Cllr range: 0.40 to 0.54). The results indicate that in LR-based FVC it is important to assess the stability of the system as a function of the samples of speakers used (Cllr range) rather than just reporting a single Cllr value based on one configuration of speakers in each set. The study contributes to the general debate on reporting uncertainty in LR computation.

查看原文本刊更多论文

说话人采样在基于似然比的取证语音比较中的作用

在法医声音比较（FVC）领域，专家们面临着越来越大的压力，要求他们证明他们在个案工作中得出的结论的有效性和可靠性。利用说话者数据库计算数字似然比（LR）的完全数据驱动方法的一个好处是，可以凭经验估计有效性和可靠性。然而，关于LR输出的稳定性，作为训练、测试和参考数据集中使用的特定扬声器采样的函数，人们知之甚少。本研究使用两大组共振峰数据来解决这个问题：广东话句子词尾助词/a/和英式英语填充停顿UM。实验被复制了100次，改变了1）训练、测试和参考说话者，2）仅训练说话者，3）仅测试说话者，4）仅参考说话者。结果表明，对于广东话和英语变量，改变三组中的说话者对系统稳定性的影响最大，/a/的Cllr在0.60-0.97之间变化，UM在0.32-1.33之间变化。然而，这种变化主要是由于测试集中不确定性的影响。对于/a/（Cllr范围：0.76至0.88），仅改变训练扬声器对系统稳定性的影响最小，而不同的参考扬声器对UM的影响最小（Cllr范围：0.40至0.54）。结果表明，在基于LR的FVC中，重要的是评估系统的稳定性，将其作为所用扬声器样本的函数（Cllr范围），而不仅仅是基于每组扬声器的一种配置报告单个Cllr值。该研究为LR计算中报告不确定性的一般性辩论做出了贡献。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

International Journal of Speech Language and the Law Multiple-

CiteScore

1.00

自引率

25.00%

发文量

期刊介绍： The International Journal of Speech, Language and the Law is a peer-reviewed journal that publishes articles on any aspect of forensic language, speech and audio analysis. Founded in 1994 as Forensic Linguistics, the journal changed to its present title in 2003 to reflect a broadening of academic coverage and readership. Subscription to the journal is included in membership of the International Association of Forensic Linguists and the International Association for Forensic Phonetics and Acoustics.