Automatic Generation of Grouping Structure based on the GTTM

This paper describes an automatic grouping system, which segments the music into units such as phrases or motives, based on the Generative Theory of Tonal Music (GTTM in short, hereafter). The GTTM is considered to be one of the most promising theories of music in regard to computer implementation; however, no order in applying those rules is given and thus, more often than not, may result in conflict among them. To solve this problem, we introduce adjustable parameters, which enable us to give priority among rules. We show the experimental results that our method outperformed the baseline performance by over thirty percent, tuning the parameters. In addition, we show that the system displays the time-span tree based on these grouping rules together with metric information given by input MusicXML.