Content-based music classification
Yu-Lung Lo, Yi-Chang Lin · 2010
The music classification techniques can be discriminated into two categories — based by music content-based classification and training by learning machine classification. Both have their advantages and disadvantages. For music content-based classifications, most of the approaches are based on single music feature, such as melody or chord, and the accuracy is up to 70% in few genres of music. However, the accuracy for classification of most music genres is lower. In this paper, we study the features of music content and use the multiple features of music data to improve the accuracy of music classification. Our performance studies shown that the higher accuracy can be achieved for classification of classical music by using multiple features of music content for classification.