Artificial Intelligence in Innovation of Investigative Interviews Speech-To-Text and Text Analysis Using Machine Learning

The project has delivered several innovative solutions, including speech-to-text (STT) for the police and for the Office of the Director of Public Prosecutions (DPP) through the development of the police’s own transcription solution, Skriber. The following deliveries have been completed: Interviews: Skriber was put into use in 2024 and systematically tested in interviews with good results. Court cases: Approximately 400 hours were transcribed from two high-profile trials in collaboration with the prosecution authorities. In addition, court proceedings have also been transcribed retrospectively. Pilot 2025 (Vest/Oslo Police Districts): Transcription is in use on live operational data within interviews, collection, forensic work, and PPS; training was completed in spring 2025. Crisis exercises 2024: Participated in three exercises involving transcription and testing of AI summarisation; results were mixed but partly promising, and the work provided important test data. All planned PoCs and pilots for speech-to-text have been delivered, and the work has created positive spillover effects: when one solution works, it often becomes the starting point for the next improvement. For example, an early PoC in forensic work has already evolved into a pilot. In addition, automation has accelerated the workflow—audio files can now be sent for transcription automatically, without manual intermediate steps. The project has also produced a substantial number of contributions in the form of scientific articles, webinars, and participation in Norwegian and international arenas. AI4Interviews’ forensic solutions have received clear recognition: finalist for the Digitalisation Award 2025, 3rd place in the GIMI Awards (Most Innovative Project – Public Sector), and winner of the Europol Excellence Award in Innovation in the category “Technical Solutions”. The work has been interdisciplinary and innovation-driven, and the team has grown throughout the period. The biggest challenges have not been the ideas, but the framework conditions around them: legal clarifications and the need for a robust and powerful AI platform within the police.

The project has had several good innovative deliveries in the police. The project has delivered speech-to-text (TTT) in the police and to the Supreme Prosecution Service by developing the police's own transcription solution Skriber. All planned PoCs and Pilots for TTT have been delivered. Several PoCs have been delivered, and a number of spin-offs are well underway, confirming that innovation breeds innovation. We worked with police case related to court, crime Scene investigation, mobile app for interviews done by the patrols, and crises. Also, we work with robotics. Related to publications and representation, the project delivers scientific articles, webinars and participation in Norwegian and international arenas, which we are very satisfied with. The work is interdisciplinary and innovative, where the team has grown recently.

Every year, the Norwegian police carry out thousands of investigative interviews of different types. Generally, these are either transcribed manually (dialog reports) in full or partially, or reports are written as a summary of the interviews. This is very time-consuming and tedious work for the investigators and police officers. Furthermore, the number of investigative interviews related to crimes like organised crime, violence, child abuse and economic crime, is expected to increase continuously. Machine learning (ML) has been revolutionizing the fields of speech-to-text (STT) and text analysis (TA). While such technology has existed for some time, it has only been recently that scientists have developed deep learning models appropriate for language understanding tasks, and it has only been recently that they could effectively train them with massive amounts of data, thus producing far more practical models than what has existed in the past. ML for Norwegian has existed for some time already and is continuing to develop at an incredible speed. Further, using ML to perform text analysis of the interview text files has promising and exciting opportunities to support an investigation of crime. For instance, ML can be used to find patterns and contexts related to places, names, organizations and events. The design of this project combines innovation and applied research, builds upon a “building-blocks”, experiences and expands the scope from an ongoing pre-study within applied research. The pre-study started in September 2020 as a cooperation between NTNU CCIS and Oslo Police District. We have so far learned that “speech-to-text” for Norwegian already exists in use in the market with inspiring results that have been found very promising by the Norwegian police. Thus, our research focuses on assessing the readiness of speech-to-text technology for police work, and also develops and assesses a user interface for such tools that the police would be ready to adopt.