ACOUSTIC FEATURE EXTRACTION BY STATISTICS BASED LOCAL BINARY PATTERN FOR ENVIRONMENTAL SOUND CLASSIFICATION

Classification of environmental sounds is a fundamental pro-cedure for a wide range of real-world applications. In this pa-per, we propose a novel acoustic feature extraction method for classifying the environmental sounds. The proposed method is motivated from the image processing technique, local bi-nary pattern (LBP), and works on a spectrogram which forms two-dimensional (time-frequency) data like an image. Since the spectrogram contains noisy pixel values, for improving classification performance, it is crucial to extract the features which are robust to the fluctuations in pixel values. We ef-fectively incorporate the local statistics, mean and standard deviation on local pixels, to establish robust LBP. In addi-tion, we provide the technique of L2-Hellinger normalization which is efficiently applied to the proposed features so as to further enhance the discriminative power while increasing the robustness. In the experiments on environmental sound clas-sification using RWCP dataset that contains 105 sound cat-egories, the proposed method produces the superior perfor-mance (98.62%) compared to the other methods, exhibiting significant improvements over the standard LBP method as well as robustness to noise and low computation time. Index Terms — environmental sound, classification, spectrogram, local binary pattern 1