This work proposes an automatic recognition system for recognizing audio events. First, an audio signal is converted into a spectrogram by short time Fourier transform. The acoustic background noises in the spectrogram are reduced by box filtering. The contrast of the spectrogram is then enhanced by VAR operation. With the enhanced spectrogram, this work further proposes a novel dynamic local binary pattern (DLBP) feature based on human auditory system. Finally, the DLBP features are fed to multi-class support vector machines to achieve the audio event recognition. The experimental results on 16 classes of audio events demonstrate the performance of the proposed audio event recognition system.