Towards a Human-Friendly Melody Characterization by Automatically Induced Rules

There is an increasing interest in music information retrieval for reference, motive, or thumbnail extraction from a piece in order to have a compact and representative representation of the information to be retrieved. One of the main references for music is its melody. In a practical environment of symbolic format collections the information can be found in standard MIDI file format, structured as a number of tracks, usually one of them containing the melodic line, while the others contain the accompaniment. The goal of this work is to analyse how statistical rules can be used to characterize a melody in such a way that one can understand the solution of an automatic system for selecting the track containing the melody in such files.