Multi-feature indexing for music data

The management of large collections of music data in a multimedia database has received much attention in the past few years. In the most of current works, the researchers extract the features, such as melodies, rhythms and chords, from the music data and develop indices that will help to retrieve the relevant music quickly and improve the query accuracy. Several reports have pointed out that these features of music can be transformed and represented in the forms of music feature strings. However, these approaches lack of scalability while increasing the music data. Recently, we proposed an approach to transform the music data into a numeric forms and developed an index structure base on R-tree for effective retrieval. This numeric index approach performed more efficiently than existing string index approaches for music database retrieval. In this paper, we will extend our study to develop a multi-feature numeric index structure for music data. Our experimental results show that the new proposed structure outperforms existing multi-feature string index approaches.