我们能否识别法证场景中的未知音频录音环境?

Denise Moussa, Germans Hirsch, Christian Riess
{"title":"我们能否识别法证场景中的未知音频录音环境?","authors":"Denise Moussa, Germans Hirsch, Christian Riess","doi":"arxiv-2405.02119","DOIUrl":null,"url":null,"abstract":"Audio recordings may provide important evidence in criminal investigations.\nOne such case is the forensic association of the recorded audio to the\nrecording location. For example, a voice message may be the only investigative\ncue to narrow down the candidate sites for a crime. Up to now, several works\nprovide tools for closed-set recording environment classification under\nrelatively clean recording conditions. However, in forensic investigations, the\ncandidate locations are case-specific. Thus, closed-set tools are not\napplicable without retraining on a sufficient amount of training samples for\neach case and respective candidate set. In addition, a forensic tool has to\ndeal with audio material from uncontrolled sources with variable properties and\nquality. In this work, we therefore attempt a major step towards practical forensic\napplication scenarios. We propose a representation learning framework called\nEnvId, short for environment identification. EnvId avoids case-specific\nretraining. Instead, it is the first tool for robust few-shot classification of\nunseen environment locations. We demonstrate that EnvId can handle forensically\nchallenging material. It provides good quality predictions even under unseen\nsignal degradations, environment characteristics or recording position\nmismatches. Our code and datasets will be made publicly available upon acceptance.","PeriodicalId":501178,"journal":{"name":"arXiv - CS - Sound","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Can We Identify Unknown Audio Recording Environments in Forensic Scenarios?\",\"authors\":\"Denise Moussa, Germans Hirsch, Christian Riess\",\"doi\":\"arxiv-2405.02119\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Audio recordings may provide important evidence in criminal investigations.\\nOne such case is the forensic association of the recorded audio to the\\nrecording location. For example, a voice message may be the only investigative\\ncue to narrow down the candidate sites for a crime. Up to now, several works\\nprovide tools for closed-set recording environment classification under\\nrelatively clean recording conditions. However, in forensic investigations, the\\ncandidate locations are case-specific. Thus, closed-set tools are not\\napplicable without retraining on a sufficient amount of training samples for\\neach case and respective candidate set. In addition, a forensic tool has to\\ndeal with audio material from uncontrolled sources with variable properties and\\nquality. In this work, we therefore attempt a major step towards practical forensic\\napplication scenarios. We propose a representation learning framework called\\nEnvId, short for environment identification. EnvId avoids case-specific\\nretraining. Instead, it is the first tool for robust few-shot classification of\\nunseen environment locations. We demonstrate that EnvId can handle forensically\\nchallenging material. It provides good quality predictions even under unseen\\nsignal degradations, environment characteristics or recording position\\nmismatches. Our code and datasets will be made publicly available upon acceptance.\",\"PeriodicalId\":501178,\"journal\":{\"name\":\"arXiv - CS - Sound\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-05-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Sound\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2405.02119\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Sound","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2405.02119","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

录音可在刑事调查中提供重要证据。其中一种情况是将录音与录音地点联系起来进行取证。例如,语音信息可能是缩小犯罪候选地点的唯一调查线索。迄今为止,有几项工作提供了在相对干净的录音条件下进行封闭式录音环境分类的工具。然而,在法医调查中,候选地点是针对具体案件的。因此,如果不对每个案件和各自的候选集进行足够数量的训练样本的再训练,封闭集工具是不适用的。此外,法证工具还必须处理来自不受控制来源的音频资料,这些资料的属性和质量各不相同。因此,在这项工作中,我们尝试向实际取证应用场景迈出重要一步。我们提出了一个表征学习框架,称为 EnvId,是环境识别的简称。EnvId 避免了针对具体案例的训练。取而代之的是,它是第一款用于对未见环境位置进行稳健的少镜头分类的工具。我们证明了 EnvId 能够处理具有法医挑战性的材料。即使在信号衰减、环境特征或记录位置不匹配的情况下,它也能提供高质量的预测。我们的代码和数据集将在通过验收后公开发布。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Can We Identify Unknown Audio Recording Environments in Forensic Scenarios?
Audio recordings may provide important evidence in criminal investigations. One such case is the forensic association of the recorded audio to the recording location. For example, a voice message may be the only investigative cue to narrow down the candidate sites for a crime. Up to now, several works provide tools for closed-set recording environment classification under relatively clean recording conditions. However, in forensic investigations, the candidate locations are case-specific. Thus, closed-set tools are not applicable without retraining on a sufficient amount of training samples for each case and respective candidate set. In addition, a forensic tool has to deal with audio material from uncontrolled sources with variable properties and quality. In this work, we therefore attempt a major step towards practical forensic application scenarios. We propose a representation learning framework called EnvId, short for environment identification. EnvId avoids case-specific retraining. Instead, it is the first tool for robust few-shot classification of unseen environment locations. We demonstrate that EnvId can handle forensically challenging material. It provides good quality predictions even under unseen signal degradations, environment characteristics or recording position mismatches. Our code and datasets will be made publicly available upon acceptance.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信