N-Gram Chord Profiles for Composer Style Representation

This paper studies the problem of using weighted Ngrams of chord sequences to construct the profile of a composer. The N-gram profile of a chord sequence is the collection of all N-grams appearing in a sequence where each N-gram is given a weight proportional to its beat count. The N-gram profile of a collection of chord sequences is the simple average of the N-gram profile of all the chord sequences in the collection. Similarity of two composers is measured by the cosine of their respective profiles, which has a value in the range [0, 1]. Using the cosine-based similarity, a group of composers is clustered into a hierarchy, which appears to be explicable. Also, the composition style can be identified using N-gram signatures.