Press Releases

The InsightPersona research tool takes media literacy in political education to the next level. The AI-based analysis software identifies faces and voices in large archives in seconds. With the help of a chatbot and a semantic search, the analyzed archive can be used for research purposes. In the intuitively designed dashboard, the results can be processed to answer further questions. Journalists, teachers, publishers, software providers and those working in political education can find out more about the Fraunhofer IDMTproject at the didacta fair in Stuttgart from 11 to 15 February 2025.

A well-functioning voice is an essential prerequisite for teachers in their daily work. With VoiceTracker, the Fraunhofer IDMT is working on a solution that offers teachers preventive support for the health of their voice. The software analyzes voice quality in real time and detects potential voice problems at an early stage. Interested teachers and companies involved in preventive health care can find out more about VoiceTracker at the didacta education trade fair in Stuttgart from February 11 to 15, 2025.

Fraunhofer IDMT will showcase its Content Verification Toolbox — a sophisticated suite of tools designed to support and enhance media content verification at IBC 2024. These tools provide robust, explainable, AI-driven solutions for media professionals investigating both audio and audio-visual content.

At the International Broadcasting Convention (IBC) in Amsterdam, the Fraunhofer Institute for Digital Media Technology IDMT will be presenting a solution that uses AI to identify faces and voices in large media collections. The solution "InsightPersona" provides evaluations of the presence of people, groups of people, and conversation content in a matter of seconds. In combination with information on speech intelligibility or excitement in the voice, it also offers new perspectives for searches in video archives and databases.

Zander Labs has selected the Fraunhofer Institute for Digital Media Technology IDMT in Oldenburg as a strategic partner for the project “Neuroadaptivity for Autonomous Systems” (NAFAS) to develop state-of-the-art, unobtrusive hardware for next-generation mobile EEG devices.

Luca Cuccovillo, Patrick Aichroth, and Thomas Köllmer received the Best Paper Award at the 2024 AES International Conference on Audio Forensics in Denver (Colorado, USA) at the end of June. They described a method which not only makes it possible to determine whether the speech is synthesized or not, but also provides a score indicating how reliable this recognition is.

Loud or unpleasant driving noises can impair the enjoyment of music in the car. Some sound systems therefore dynamically adjust the volume and bass. However, individual sound preferences are not taken into account. A study from Fraunhofer IDMT in Oldenburg has now investigated the influence of background noise on the personal sound experience while driving – and shows how an adjustment of individual sound preferences once could improve the sound in the vehicle (and beyond).

Some children learn to talk sooner than others. This makes it difficult to detect anomalies in language acquisition immediately and in the first years of their lives. However, to give children affected by such a developmental delay a good start when they go to school, early support is essential. Together, Fraunhofer IDMT in Oldenburg and the Klett Group are exploring to what extent technological solutions can help nursery teachers to identify support needs.