Automatic Classification of Classical Music Compositions

Abstract

In this study, we used several algorithms to classify classical music composers on a dataset called MusicNet. After extracting quantitive features from each composition in a workable format, composer of each composition is predicted by using K-Nearest Neighbor, Support Vector Machine and Decision Tree algorithms. Several experiments are performed on different data subsets that includes two, five and ten different composers. It is observed that the classification accuracy obtained in our experiments are comparable to the results of other similar studies in research literature. This electronic document is a "live" template and already defines the components of your paper [title, text, heads, etc.] in its style sheet.