A deep learning approach for mapping music genres

Deep feature learning methods have been aggressively applied in the field of music tagging retrieval Genre categorization, mood classification, and chord detection are the most common tags from local spectral to temporal structure. Convolutional Neural networks (CNNs) using kernels extract the local features that are in different levels of hierarchy while Recurrent Neural Networks (RNNs) discover the global features to understand the temporal context, CRNN architectures as a powerful music tagging utilize the benefits of the both CNN and RNN structures. In this article a CRNN structure on MagnaTagA Tune dataset is proposed. The AUC-ROC index for the proposed architecture is 0.893 which shows its superiority rather than traditional structures on the same database. The merging mechanism to obtain 50 tags from the whole 188 existing tags of this dataset and simple CRNN architecture designed for tag discovering are the main contribution of this paper.