You are currently viewing HENSOLDT Analytics’ Contribution to CSI Network Analysis for the H2020 Project ROXANNE

HENSOLDT Analytics’ Contribution to CSI Network Analysis for the H2020 Project ROXANNE

  • Post author:
  • Post category:Projects
In January 2021, SAIL LABS Technology GmbH was acquired by the sensor specialist HENSOLDT and became HENSOLDT Analytics.

Collecting and analysing the evidence of a crime can easily exceed the capabilities of teams as investigators often deal with large and dynamically changing criminal cases.

The ROXANNE (Real time network, text and speaker analytics for combating organized crime) is an EU-funded H2020 collaborative research and innovation project, which focuses on providing robust and efficient means of identifying criminals by combining the advances in speechlanguage and video technologies with criminal network analysis. The aim of the project is to develop a novel platform, reducing the investigation time and costs for law enforcement agencies.

The project consortium is comprised of 24 organisations from 16 countries, out of which 11 are law enforcement agencies. As one of the partners, SAIL LABS (now HENSOLDT Analytics contributes to the project providing its expertise in the field of speech and language processing technologies.

HENSOLDT Analytics recently contributed to the development of the CSI case study, in which the idea was to analyse the conversational networks in selected episodes of the CSI: Crime Scene Investigation series. As part of this study, a data collection of conversations among the characters was prepared; automatic speech recognition and speaker clustering technologies were applied on the audio, and network analysis techniques were used to uncover the hidden patterns regarding the behavior and relations among individuals, finally leading to a detailed knowledge of “who talked to whom” from the videos.

You can find out more about network analysis and this CSI case study on ROXANNE´s website.

The ROXANNE project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement № 833635.