Content-based music classification

Abstract

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.

Graphical Layout of the Musical Preferences Studies: An Overview on How the Studies on Musical Tastes Are Conducted

“…Furthermore, by applying and discovering the relationship between the genre and musical features, many studies compete on automatic genre classifications (Rosner et al, 2014;Vatolkin, Rötter, & Weihs, 2014;Cheng, Yang, Lin, Liao, & Chen, 2008). Although genre categorization has traditionally been performed manually and "human beings were not able to classify correctly more than 76% of the music pieces" (Lippens, Martens, & De Mulder, 2004), nowadays by considering multiple features of music, automatic genre classification increases the accuracy of classification to 80% (Costa, Oliveira, Koerich, Gouyon, & Martins, 2012;Lo & Lin, 2010;. Consequently, genre as the most well-acknowledged music classification cooperates in music preference studies in both direct and indirect manner.…”

Categorization of Alpha Wave Music by SOM Reduction

“…Lo et al investigated the content-based features of the alpha wave music and develop the distance function for music classification [11]. The music features can be the occurrence frequencies of notes, rhythms, and etc.…”

“…The experimental music database used in this study is collected by Lo et al [11,19] including six music genres -blues, classical, folk, jazz, pop and alpha wave music. Among them, there are 150 pieces music for each genre except alpha wave music which has only 87 pieces due to difficult collection.…”

“…The contents of music provided diverse musical features such as: melody, rhythm and chords, etc., which may represent a music genre. Therefore, content-based music retrieval and classification are important research fields for music databases [8,9,10,11]. In this research, we will investigate the features of the alpha wave music for analyzing and tries to categorize the alpha wave music by Self Organizing Map (SOM) approach [12,13,14].…”