A Comparative Analysis of Music Similarity Measures in Music Information Retrieval Systems

초록

The digitization of music has seen a considerable increase in audience size from a few localized listeners to awider range of global listeners. At the same time, the digitization brings the challenge of smoothly retrievingmusic from large databases. To deal with this challenge, many systems which support the smooth retrieval ofmusical data have been developed. At the computational level, a query music piece is compared with the restof the music pieces in the database. These systems, music information retrieval (MIR systems), work forvarious applications such as general music retrieval, plagiarism detection, music recommendation, andmusicology. This paper mainly addresses two parts of the MIR research area. First, it presents a generaloverview of MIR, which will examine the history of MIR, the functionality of MIR, application areas of MIR,and the components of MIR. Second, we will investigate music similarity measurement methods, where weprovide a comparative analysis of state of the art methods. The scope of this paper focuses on comparativeanalysis of the accuracy and efficiency of a few key MIR systems. These analyses help in understanding thecurrent and future challenges associated with the field of MIR systems and music similarity measures.

키워드