Idiom-independent Harmonic Pattern Recognition Based on a Novel Chord Transition Representation

In this paper, a novel chord transition representation (Cambouropoulos 2012), that draws on the interval function between two collections of notes proposed by Lewin (1959), is explored in a harmonic recognition task. This representation allows the encoding of chord transitions at a level higher that individual notes that is transposition-invariant and idiom-independent (analogous to pitch intervals that represent transitions between notes). A harmonic transition between two chords is represented by a Directed Interval Class (DIC) vector. The proposed 12dimensional vector encodes the number of occurrence of all directional interval classes (from 0 to 6 including +/for direction) between all the pairs of notes of two successive chords. Apart from octave equivalence and interval inversion equivalence, this representation preserves directionality of intervals (up or down). A small database is constructed comprising of chord sequences derived from diverse music idioms/styles (tonal music, different traditional harmonic idioms, 20 century nontonal harmonic idioms). The proposed DIC representation is evaluated on a harmonic recognition task, i.e. we examine the accuracy of recognition of harmonic queries in this database. The results of the algorithm are judged by human music analysis experts. It is suggested that the proposed idiom-independent chord transition representation is adequate for representing harmonic relations in music from diverse musical idioms (in equal temperament) and, therefore, may provide a most appropriate framework for harmonic processing in the domain of computational ethnomusicology.