Paper Details

Music genre is clear cut names made by people to classes bits of music. A music genre classification is portrayedby the basic attributes shared by its individuals. These attributes ordinarily are identified with the instrumentation, harmoniccontent, and rhythmic structure of the music. Genre is usually used to structure the expansive accumulations of musicaccessible on the Web. Presently, music genre annotation is performed manually. Automatic music genre classificationarrangement can help or supplant the human client in this procedure and would be a valuable expansion to music dataretrieval frameworks. Likewise, Automatic music genre classification gives a structure to creating and assessing highlightsfor a substance based examination of musical signals. In this survey paper, the automatic music genre into a progressivesystem of music genre is investigated. All the more particularly, three feature sets for representing pitch content, rhythmiccontent and timbral texture are proposed. The performance and relative importance of the proposed features are investigatedby training statistical pattern recognition classifiers using real-world audio collections. We compare the classificationaccuracy rate of various deep learning models with a set of well-known learning models including Deep Neural Network,Convolution Neural Network, Recurrent Neural Network in combination with hand-crafted audio features for a genreclassification task on a public dataset.

Maulik Desai, Jay Rodge, Kapil Sahu, Advait Kulkarni, Prof. Bhavana Bahikar, “SURVEY on Music Genre Recognition using Deep Learning”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 4, Issue 11, pp. 862-865, November 2017.