Method to Detect GTTM Local Grouping Boundaries Based on Clustering and Statistical Learning

In this paper, we describe σGTTMII , a method that detects local grouping boundaries of the generative theory of tonal music (GTTM) based on clustering and statistical learning. It is difficult to implement GTTM on a computer because rules of GTTM often conflict with each other and cannot detect music structure as same manner. Previous methods have successfully implemented GTTM on a computer by introducing adjustable parameters or acquiring the priority of the rules by statistical learning. However, the values of the parameters and the priority of the rules are different depending on a piece of music. Considering these problems, we focused on the priority of the rules and we hypothesized that there are some tendency of rules which have more strong influence than other rules by the case of music. To ensure this hypothesis, we tried to classify each piece of music and tried to find the tendency of rules. Through the experiment, we found some tendency of rules and then we acquired some detectors which can analyze each piece of music more appropriately by reiterating clustering music and statistical learning.