Detection of Stream Segments in Symbolic Musical Data

A listener is thought to be able to organise musical notes into groups within musical streams/voices. A stream segment is a relatively short coherent sequence of tones that is separated horizontally from co-sounding streams and, vertically from neighbouring musical sequences. This paper presents a novel algorithm that discovers musical stream segments in symbolic musical data. The proposed algorithm makes use of a single set of fundamental auditory principles for the concurrent horizontal and vertical segregation of a given musical texture into stream segments. The algorithm is tested against a small manually-annotated dataset of musical excerpts, and results are analysed; it is shown that the technique is promising.