Conference Proceeding Article
This article presents a novel indexing framework called EMIF (Effective Music Indexing Framework) to facilitate scalable and accurate content based music retrieval. EMIF system architecture is designed based on a "classification-and-indexing" principle and consists of two main functionality layers: 1) a novel semantic-sensitive classification to identify input music's category and 2) multiple indexing structures - one local indexing structure corresponds to one semantic category. EMIF's layered architecture not only enables superior search accuracy but also reduces query response time significantly. To evaluate the system, a set of comprehensive experimental studies have been carried out using large test collection and EMIF demonstrates promising performance over state-of-theart approaches.
Content based music retrieval, Indexing structure, Retrieval
Computer Sciences | Databases and Information Systems
Data Management and Analytics
ICMR '15: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval: Shanghai, June 23-26, 2015
City or Country
SHEN, Jialie; MEI, Tao; TAO, Dacheng; LI, Xuelong; and RUI, Yong.
EMIF: Towards a scalable and effective indexing framework for large scale music retrieval. (2015). ICMR '15: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval: Shanghai, June 23-26, 2015. 543-546. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3545
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.