https://scholars.lib.ntu.edu.tw/handle/123456789/636483
標題: | An integrated approach to music boundary detection | 作者: | Su, Min Yian YI-HSUAN YANG Lin, Yu Ching HOMER H. CHEN |
公開日期: | 1-十二月-2009 | 來源出版物: | Proceedings of the 10th International Society for Music Information Retrieval Conference, ISMIR 2009 | 摘要: | Music boundary detection is a fundamental step of music analysis and summarization. Existing works use either unsupervised or supervised methodologies to detect boundary. In this paper, we propose an integrated approach that takes advantage of both methodologies. In particular, a graph-theoretic approach is proposed to fuse the results of an unsupervised model and a supervised one by the knowledge of the typical length of a music section. To further improve accuracy, a number of novel mid-level features are developed and incorporated to the boundary detection framework. Evaluation result on the RWC dataset shows the effectiveness of the proposed approach. © 2009 International Society for Music Information Retrieval. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/636483 | ISBN: | 9780981353708 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。