Comparing repetition-based melody segmentation models

M.E. Rodríguez López, Bas de Haas, Anja Volk

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    Abstract

    This paper reports on a comparative study of computational
    melody segmentation models based on repetition detection. For the comparison we implemented five repetition-based segmentation models, and subsequently evaluated their capacity to automatically find melodic phrase boundaries in a corpus of 200 folk melodies. We systematically investigate the effects that the choice of melodic representation, similarity measure, and parameter settings have on each model’s performances. We discuss at length issues such as parameter sensitivity, generalization capability, and efficiency. The best performing model employs a similarity matrix to identify repetitions, and selects which repetitions are used to segment the input melody using an optimisation-based search algorithm.
    Original languageEnglish
    Title of host publicationProceedings of the 9th Conference on Interdisciplinary Musicology (CIM14)
    Place of PublicationBerlin
    PublisherSIMPK and ICCMR
    Pages143-148
    Number of pages6
    Publication statusPublished - 2014
    EventConference on Interdisciplinary Musicology - Berlin, Germany
    Duration: 4 Dec 20146 Dec 2014

    Conference

    ConferenceConference on Interdisciplinary Musicology
    Country/TerritoryGermany
    CityBerlin
    Period4/12/146/12/14

    Keywords

    • melody segmentation
    • repetition detection
    • Music Information Retrieval
    • music information processing
    • digital musicology
    • machine learning

    Fingerprint

    Dive into the research topics of 'Comparing repetition-based melody segmentation models'. Together they form a unique fingerprint.

    Cite this