MUSIC GENRE CLASSIFICATION USING MACHINE AND DEEP LEARNING TECHNIQUES: A REVIEW

Abstract

The ability to accurately classify music into their genres is the aim of a music genre classification system. This is broadly achieved by extracting good features from the songs and employing a good classification system. Various song libraries which are the datasets, input formats which are the features extracted from the datasets, machine learning techniques, deep learning techniques which have been employed in existing works have all delivered various degree of success. This paper therefore aims to review some of the machine learning and deep learning techniques that have been developed to accurately classify music into their genres. An evaluation of the different techniques reviewed in this paper in the context of their demonstrated results for music genre classification will also be examined.