A Study of Feature Extraction and Classification Method for Music Objects in MusicXML

• Main Authors: Yu-Chih Shen, 沈裕智
• Other Authors: Jia-Lien Hsu
• Format: Others
• Language: zh-TW
• Published: 2005
• Online Access: http://ndltd.ncl.edu.tw/handle/01800011306852746030

碩士 === 輔仁大學 === 資訊工程學系 === 93 === In the music information retrieval field, the most important topic is to extract the feature which represents the content from the music objects. Therefore, the content feature is useful for music analysis, music retrieval and other services. In this paper, our data form is MusicXML. We extract the structural feature from the classical music object and it is based on music theory and music form. According to the hierarchical rule of music form, we construct a tree structure which is called MF-tree, that is provided with the music theory feature and structure in the MF-tree. At the same time, we also propose the dissimilarity function of MF-tree to calculating the dissimilarity of music objects. Finally, we adapt the hierarchical clustering and system implementation to show the clustering effectively.