We extracted Mel-Frequency Cepstral Coefficients (MFCCs) features for this task. MFCC are short-term spectral-based features and have been widely used in speech recognition [13] and audio event classification. We ex- tracted 12MFCC coefficients from the original audio signal using a sliding window of 40ms at fixed intervals of 20ms. The number of training and testing frames for the different methods is shown in Table 1. Note that there is no need for unusual event training data for our approach. For the un- supervised HMM, there is no need for training data. The percentage of frames for unusual events in the test sequence is around