Melodic segmentation: evaluating the performance of algorithms and musical experts

We review several segmentation algorithms, qualitatively highlighting their strengths and weaknesses. We also provide a detailed quantitative evaluation of two existing approaches, Temperley\u27s Grouper and Cambouropoulos\u27 Local Boundary Detection Model. In order to facilitate the comparison of an algorithm\u27s performance with human behavior, we compiled a corpus of melodic excerpts in different musical styles and collected individual segmentations from 19 musicians. We then empirically assessed the algorithms\u27 performance by observing how well they can predict both the musicians\u27 segmentations and data taken from the Essen folk song collection