Effects of language mismatch in automatic forensic voice comparison using deep learning embeddings

In forensic voice comparison, deep learning has become widely popular recently. It is mainly used to learn speaker representations, called embeddings or embedding vectors. Speaker embeddings are often trained using corpora mostly containing widely spoken languages. Thus, language dependency is an important factor in automatic forensic voice comparison, especially when the target language is linguistically very different from that the model is trained on. In the case of a low-resource language, developing a corpus for forensic purposes containing enough speakers to train deep learning models is costly. This study aims to investigate whether a model pre-trained on multilingual (mostly English) corpus can be used on a target low-resource language (here, Hungarian), not represented by the model. Often multiple samples are not available from the offender (unknown speaker). Samples are therefore compared pairwise with and without speaker enrollment for suspect (known) speakers. Two corpora are used that were developed especially for forensic purposes and a third that is meant for traditional speaker verification. Speaker embedding vectors are extracted by the x-vector and ECAPA-TDNN techniques. Speaker verification was evaluated in the likelihood-ratio framework. A comparison is made between the language combinations (modeling, LR calibration, and evaluation). The results were evaluated by Cllr_min and EER metrics. It was found that the model pre-trained on a different language but on a corpus with a significant number of speakers can be used on samples with language mismatch. Sample duration and speaking style also seem to affect the performance.     

比较与借鉴：中外青年志愿服务现状透视

国外发达国家青年志愿服务工作已逐渐步入组织化、规范化和系统化的轨道。通过中外志愿服务的比较发现,我国青年志愿服务水平与社会成员的需求仍然有较大的差距。应借鉴与吸收国外的成功经验,以更好地推动我国青年志愿服务工作的持续发展。     

Could lessons have been drawn from New Zealand for England’s NHS reforms?

This article argues that New Zealand (NZ) could be an important case for drawing health system reform lessons from for the English National Health Service. Reasons for this are outlined, including the close similarities between the two countries and their health systems. The article describes the diverging health reform agendas of conservative governments in both countries, noting a series of lessons for England that might have been drawn from NZ. Explanations for the differing reform agendas are then offered.     

3种骨骼DNA提取方法的应用效果比较

目的对3种方法提取骨骼DNA的效果进行比较,为实际应用中选择方法提供参考。方法应用骨骼孵化液法、DNA Investigator试剂盒法和CTAB法对同一骨骼样本进行脱钙、消化、提取DNA,用紫外分光光度计检测DNA的浓度值;使用Identifilerplus试剂盒进行PCR扩增,3130xl型遗传分析仪检测分型,并用SPSS 19.0软件对各项实验结果进行统计分析。结果 1g骨粉样本经上述3种方法提取,得到的DNA浓度分别为26.53ng/μL±5.47ng/μL、23.63ng/μL±4.56ng/μL、14.93ng/μL±3.88ng/μL;单因素方差分析表明3组数据之间差异性具有统计学意义。PCR扩增后电泳检测结果显示,骨骼孵化液法和DNA Investigator试剂盒法基因座检出率和峰值大致相同,均优于CTAB法。结论本文比较的3种方法均可用于骨骼样本的实际检案,检出率较高的两种方法可作为优选方案。     

交通事故归责原则与损害赔偿理论研究

《道路交通事故处理办法》与《中华人民共和国民法通则》关于道路交通事故的归则原则完全不同 ,这导致了交通事故损害赔偿的不同。分析比较了各主要国家对交通事故的归责原则 ,并且从法学理论上对之进行研究。认为汽车与非机动车、行人发生的交通事故 ,应采取无过错责任原则 ,才更能体现法的公平与正义     

Lessons learned from inter-laboratory studies of carbon isotope analysis of honey

Forensic application of carbon isotope ratio measurements of honey and honey protein to investigate the degree of adulteration with high fructose corn syrup or other C₄ plant sugars is well established. These measurements must use methods that exhibit suitable performance criteria, particularly with regard to measurement uncertainty and traceability – low levels of adulteration can only be detected by methods that result in suitably small measurement uncertainties such that differences of 1‰ or less can be reliably detected. Inter-laboratory exercises are invaluable to assess the state-of-the art of measurement capabilities of laboratories necessary to achieve such performance criteria. National and designated metrology institutes from a number of countries recently participated in an inter-laboratory assessment (CCQM-K140) of stable carbon isotope ratio determination of bulk honey. The same sample material was distributed to a number of forensic isotope analysis laboratories that could not participate directly in the metrological comparison. The results from these studies have demonstrated that the majority of participants provided isotope delta values with acceptable performance metrics; that all participants ensured traceability of their results; and that where measurement uncertainties were reported; these were fit-for-purpose. A number of the forensic laboratories only reported precision rather than full estimates of measurement uncertainty and this was the major cause of the few instances of questionable performance metrics. Reporting of standard deviations in place of measurement uncertainties is common practice outside metrology institutes and the implications for interpretations of small differences in isotopic compositions are discussed. The results have also highlighted a number of considerations that are useful for organisers of similar inter-laboratory studies in the future.     

Quantitative Statistics and Identification of Tool‐Marks

This study was designed to establish a feature identification method of tool‐mark 2D data. A uniform local binary pattern histogram operator was developed to extract the tool‐mark features, and the random forest algorithm was adopted to identify these. The presented method was used to conduct five groups of experiments with a 2D dataset of known matched and nonmatched tool‐marks made by bolt clippers, cutting pliers, and screwdrivers. The experimental results show that the proposed method achieved a high rate of identification of the tool‐mark samples generated under identical conditions. The proposed method effectively overcomes the disadvantage of unstable illumination of 2D tool‐mark image data and avoids the difficulty in mark inspection caused by manually preset parameters in the existing methods, thus reducing the uncertainty of inspected results.     

A part-declared blind testing program in firearms examination

In 2015 and 2016 the Central Unit of the Dutch National Police created and submitted 21 cartridge case comparison tests as real cases to the Netherlands Forensic Institute (NFI), under supervision of the University of Twente (UT). A total of 53 conclusions were drawn in these 21 tests. For 31 conclusions the underlying ground truth was “positive”, in the sense that it addressed a cluster of cartridge cases that was fired from the same firearm. For 22 conclusions the ground truth was “negative”, in the sense that the cartridge cases were fired from different firearms. In none of the conclusions, resulting from examinations under casework conditions, misleading evidence was reported. All conclusions supported the hypothesis reflecting the ground truth. This article discusses the design and results of the tests in more detail.