Combining Visual and Acoustic Features for Music Genre Classification

Music genre classification is a challenging task in the field of music information retrieval. Existing approaches usually attempt to extract features only from acoustic aspect. However, spectrogram also provides useful information because it describes the temporal change of energy distribution over frequency bins. In this paper, we propose the use of Gabor filters to generate effective visual features that can capture the characteristics of a spectrogram´s texture patterns. On the other hand, acoustic features are extracted using universal background model and maximum a posteriori adaptation. Based on these two types of features, we then employ SVM to perform the final classification task. Experimental results demonstrate that combining visual and acoustic features can achieve satisfactory classification accuracy on two widely used datasets.