Maël F.

Speaker recognition has many applications in conversational data, including in forensic science where Law Enforcement Agencies (LEAs) aim to assess the identity of a speaker on a specific recorded telephone call. However, speaker identification (SID) systems require initial enrollment data, whereas LEAs might start a case with text or video evidence, and few to no enrollment data. In this paper, we introduce the ROXANNE simulated dataset, a multilingual corpus of acted telephone calls following… Mehr anzeigen

Speaker recognition has many applications in conversational data, including in forensic science where Law Enforcement Agencies (LEAs) aim to assess the identity of a speaker on a specific recorded telephone call. However, speaker identification (SID) systems require initial enrollment data, whereas LEAs might start a case with text or video evidence, and few to no enrollment data. In this paper, we introduce the ROXANNE simulated dataset, a multilingual corpus of acted telephone calls following a screenplay prepared by LEAs. We also present a process to build criminal networks from SID, by addressing practical constraints of these investigations. Our process reaches a speaker accuracy of 92.4% on the simulated data and a conversation accuracy of 84.9%. We finally offer some future directions for this work. Weniger anzeigen

Criminal investigations contain sensitive and confidential material and are nonpublic by nature. Access to investigation data is very limited and restricted to only selected groups of individuals. Even for research purposes, data typically cannot be accessed freely. Within criminal investigations, data is still processed manually to a large extent. Solutions provided for automation of this processing—or even of individual processing steps—can be assumed to have a significant impact on the work… Mehr anzeigen

Criminal investigations contain sensitive and confidential material and are nonpublic by nature. Access to investigation data is very limited and restricted to only selected groups of individuals. Even for research purposes, data typically cannot be accessed freely. Within criminal investigations, data is still processed manually to a large extent. Solutions provided for automation of this processing—or even of individual processing steps—can be assumed to have a significant impact on the work of Law Enforcement Agencies (LEAs). Automation may effectively be key to handle large and complex amounts of data in an efficient manner under the typical operating conditions of LEAs. Weniger anzeigen

Criminal investigations require manual intervention of several investigators and translators. However, the amount and the diversity of the data collected raises many challenges, and crossborder investigations against organized crime can quickly impossible to handle. We developed ROXANNE Research platform, an all-in-one platform which processes intercepted phone calls, runs state-of-the-art components such as speaker identification, automatic speech recognition or named entity detection, and… Mehr anzeigen

Criminal investigations require manual intervention of several investigators and translators. However, the amount and the diversity of the data collected raises many challenges, and crossborder investigations against organized crime can quickly impossible to handle. We developed ROXANNE Research platform, an all-in-one platform which processes intercepted phone calls, runs state-of-the-art components such as speaker identification, automatic speech recognition or named entity detection, and builds a knowledge graph of the extracted information. Our aim for this work is to do a first step in the direction of an open research platform combining speech, text, and video processing algorithms with criminal network analysis for combating organized crime. Weniger anzeigen

Criminal investigations rely on the collection of conversational data. The identity of speakers must be assessed in order to build or improve the accuracy of an existing criminal network. Investigators use social network analysis tools to identify the most central character and the different communities within the network. We introduce Crime Scene Investigation (CSI) television show as a potential candidate for criminal conversational data. We also introduce the metric of conversation accuracy… Mehr anzeigen

Criminal investigations rely on the collection of conversational data. The identity of speakers must be assessed in order to build or improve the accuracy of an existing criminal network. Investigators use social network analysis tools to identify the most central character and the different communities within the network. We introduce Crime Scene Investigation (CSI) television show as a potential candidate for criminal conversational data. We also introduce the metric of conversation accuracy in the context of criminal investigations. In this paper, a speaker identification baseline is improved by re-ranking candidate speakers based on the frequency of previous interactions between speakers and the topology of the criminal network. The proposed method can be applied to conversations involving two or more speakers. We show that our approach outperforms the baseline speaker accuracy by 1.3% absolute (1.5% relative), and the conversation accuracy by 3.7% absolute (4.7% relative) on CSI data. Weniger anzeigen

Identifying the author of a given text can be useful in historical literature, plagiarism detection, or police investigations. Authorship Attribution (AA) has been well studied and
mostly relies on a large feature engineering work. More recently, deep learning-based approaches have been explored for Authorship Attribution (AA). In this paper, we introduce BertAA, a fine-tuning of a pre-trained BERT language model with an additional dense layer and a softmax activation to perform authorship… Mehr anzeigen

Identifying the author of a given text can be useful in historical literature, plagiarism detection, or police investigations. Authorship Attribution (AA) has been well studied and
mostly relies on a large feature engineering work. More recently, deep learning-based approaches have been explored for Authorship Attribution (AA). In this paper, we introduce BertAA, a fine-tuning of a pre-trained BERT language model with an additional dense layer and a softmax activation to perform authorship classification. This approach reaches competitive performances on Enron Email, Blog Authorship, and IMDb (and IMDb62) datasets, up to 5.3% (relative) above current state-of-the-art approaches. We performed an exhaustive analysis allowing us to identify the strengths and weaknesses of the proposed method. In addition, we evaluate the impact of including additional features (e.g. stylometric and hybrid features) in an ensemble approach, improving the macro-averaged F1-Score by 2.7% (relative) on average. Weniger anzeigen

Language detection is considered a difficult task especially for similar languages, varieties, and dialects. With the growing number of online content in different languages, the need for reliable and robust language detection tools also increased. In this work, we use supervised autoencoders with a bayesian optimizer for language detection and highlights its efficiency in detecting similar languages with dialect variance in comparison to other state-of-the-art techniques. We evaluated our… Mehr anzeigen

Language detection is considered a difficult task especially for similar languages, varieties, and dialects. With the growing number of online content in different languages, the need for reliable and robust language detection tools also increased. In this work, we use supervised autoencoders with a bayesian optimizer for language detection and highlights its efficiency in detecting similar languages with dialect variance in comparison to other state-of-the-art techniques. We evaluated our approach on multiple datasets (Ling10, Discriminating between Similar Language (DSL), and Indo-Aryan Language Identification (ILI)). Obtained results demonstrate that SAE are higly effective in detecting languages, up to a 100% accuracy in the Ling10. Similarly, we obtain a competitive performance in identifying similar languages, and dialects, 92% and 85% for DSL ans ILI datasets respectively. Weniger anzeigen

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… Mehr anzeigen

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. Weniger anzeigen