Examining long-term formant distributions as a discriminant in forensic speaker comparisons under a likelihood ratio framework
Examining long-term formant distributions as a discriminant in forensic speaker comparisons under a likelihood ratio framework
复制标题
在似然比框架下检查长期共振峰分布作为法医说话人比较的判别式
DOI：
--
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Philip Harrison
中科院分区：
文献类型：
--
作者：
E. Gold;Peter French;Philip Harrison
本研究调查了使用长期共振峰分布 (LTFD) 作为法医说话人比较中的判别式。 LTFD 是针对单个录音中说话者的每个共振峰的所有值计算的分布。我们对 DyViS 数据库中 100 名讲南方标准英式英语的男性的自发语音录音进行了分析（Nolan 等人，2009 年）。录音被自动分段，以获得每个说话者至少 50 秒的元音。 iCAbS（通过合成的迭代倒谱分析）共振峰跟踪器用于自动提取和测量 F1-F4。为了评估 LTFD 的证据价值，使用多元核密度方法 (MVKD) 计算似然比 (LR)。结果发现，LTFD 总体表现良好，但不同说话人的比较比相同说话人的比较要好得多（97.4% 的比较提供了正确的支持，而 84% 的比较提供了正确的支持）。 LTFD 似乎是一个很好的判别器，可以纳入法医说话人比较分析中，并提供避免元音音素之间潜在相关问题的额外好处。本研究中基于 MVKD 的 LR 结果也被发现与 French 等人的结果相当。 （2012）和贝克尔等人。 (2008)，它使用高斯混合模型-通用背景模型 LR 方法。
This study investigates the use of long-term formant distributions (LTFDs) as a discriminant in forensic speaker comparisons. LTFDs are the distributions calculated for all values of each formant for a speaker in a single recording. Spontaneous speech recordings from 100 male speakers of Southern Standard British English were analyzed from the DyViS Database (Nolan et al. 2009). The recordings were auto-segmented to obtain a minimum of 50 seconds of vowels per speaker. The iCAbS (iterative cepstral analysis by synthesis) formant tracker was used to automatically extract and measure F1-F4. To assess the evidential value of the LTFDs, likelihood ratios (LRs) were computed using a Multivariate Kernel-Density approach (MVKD). It was found that LTFD performs well overall, but much better with different speaker comparisons than same speaker comparisons (97.4% compared to 84% of comparisons providing correct support). LTFD appears to be a good discriminant to include in forensic speaker comparison analyses and offers the added benefit of avoiding potential correlation problems between vowel phonemes. The MVKD based LR results from this study were also found to be comparable to those results in French et al. (2012) and Becker et al. (2008), which used a Gaussian Mixture Model-Universal Background Model LR approach.