Julian K{\"u}rby, Rene Grzeszick, Axel Plinge and Gernot A. Fink
Detection and Classification of Acoustic Scenes and Events (DCASE) Workshop, pages 55-59, 2016.
Budapest, Hungary
In this paper a novel approach for acoustic event detection in sensor networks is presented. Improved and more robust recognition is achieved by making use of the signals from multiple sensors. To this end, various known fusion strategies are evaluated along with a novel method using classifier stacking. A comparative evaluation of these fusion strategies is performed on two different datasets: the ITC-Irst database, and a set of smart room recordings. In both datasets, 32 distributed microphones were used for recording. Furthermore, the effect of previously observed as well as unobserved locations is investigated. The proposed stacking yields a notable improvement. The performance of recognizing events at previously unobserved locations can be improved by sorting the channels according to their posterior probabilities.