Identification of abnormal audio events based on probabilistic novelty detection

This paper exploits the novelty detection technique towards identifying hazardous situations. The proposed system elaborates on the audio part of the PROMETHEUS database which includes heterogeneous recordings and was captured under real-world conditions. Three types of environments were used: smart-home, indoors public space and outdoors public space. The multidomain set of descriptors was formed by the following features: MFCCs, MPEG-7 descriptors, Teager energy operator parameters and wavelet packets. We report detection results using three types of probabilistic novelty detection algorithms: universal GMM, universal HMM and GMM clustering. We conclude that the results are encouraging and demonstrate the superiority of the novelty detection approach against the classification one.