Today’s computers can do many amazing things. Nevertheless, there are still many "trivial" but important tasks they cannot do well. In particular, current information extraction techniques perform well, when event types are well represented in the training data, but often fail when encountering information-rich and unexpected rare events. The "DIRAC" project addressed this crucial machine weakness. The aim of the project was to design an environment-adaptive, autonomous artificial cognitive system that would detect, identify and classify possibly threatening rare events from the information derived by multiple active information-seeking audio-visual sensors.
Responsibilities of Fraunhofer IDMT
In this project, the Fraunhofer IDMT's Oldenburg Branch for Hearing, Speech and Audio Technology HSA developed an integration of different cognitive technologies on a uniform platform and created the evaluation material.