Combining multi-probe histogram and order-statistics based LSH for scalable audio content retrieval
Proceedings of the international conference on Multimedia
Hi-index | 0.00 |
Music motive extraction is an important concept to consider in music information retrieval. Among the possible applications are the creation of music databases that need of indexing tools and access in a dynamic way, copyright management and plagiarism detection, computer-aided composition, etc. This paper present an unsupervised method for automatic music motive extraction from symbolic sources, using an intervallic analysis. The results are evaluated quantitatively using a melodic similarity technique.