论文标题
Graph2Speak：使用网络知识在犯罪会话数据中改善扬声器识别
Graph2Speak: Improving Speaker Identification using Network Knowledge in Criminal Conversational Data
论文作者
论文摘要
刑事调查主要依赖于语音对话数据的收集，以识别说话者并建立或丰富现有的犯罪网络。然后，应用社交网络分析工具来确定网络中最中心的角色和不同社区。我们介绍了两个候选数据集，以供犯罪对话数据，犯罪现场调查（CSI），电视节目和Roxanne模拟数据。在刑事调查的背景下，我们还介绍了对话准确性的指标。通过基于先前互动的频率将候选扬声器重新排序，我们将Speaker识别基线提高了1.2％的绝对（相对相对1.3％），并且在CSI数据上将对话精度提高2.6％（相对3.4％），在ROXANNE模拟数据上，Absolute（相对）的绝对值（相对）相对1.2％（相对相对1.2％）和2％的绝对（2.5％相对）。
Criminal investigations mostly rely on the collection of speech conversational data in order to identify speakers and build or enrich an existing criminal network. Social network analysis tools are then applied to identify the most central characters and the different communities within the network. We introduce two candidate datasets for criminal conversational data, Crime Scene Investigation (CSI), a television show, and the ROXANNE simulated data. We also introduce the metric of conversation accuracy in the context of criminal investigations. By re-ranking candidate speakers based on the frequency of previous interactions, we improve the speaker identification baseline by 1.2% absolute (1.3% relative), and the conversation accuracy by 2.6% absolute (3.4% relative) on CSI data, and by 1.1% absolute (1.2% relative), and 2% absolute (2.5% relative) respectively on the ROXANNE simulated data.
