Convolutional Neural Networks for Music Genre Classification

T. Nakashika , C. Garcia, T. Takiguchi, University of Kobe, Japan & LIRIS, 2012

A map-based approach, which treats 2-dimensional acoustic features like image processing, has recently attracted attention in music genre classification. While this is successful at extracting local music-patterns compared with other timbral-feature-based methods, the extracted features are not sufficient for music genre classification. In this paper, we focus on appropriate feature extraction and proper classification by integrating the features. For the musical feature extraction, we calculate gray level co-occurrence matrix (GLCM) descriptors with different offsets from a short-term mel spectrogram. These feature maps are integratively classified using convolutional neural network (CNN). In our experiments, we got a large improvement of more than 10 points in the classification accuracy, compared with conventional map-based methods.