Anzeige
Erschienen in:
2018 | OriginalPaper | Buchkapitel
Similarity Measures for Music Information Retrieval
verfasst von : Michele Della Ventura
Erschienen in: Advanced Computational Methods for Knowledge Engineering
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
This article is aimed at presenting a method for the assessment of the similarity between two data strings representing the musical text analyzed on a symbolic level (music notes), in order to cluster and classify musical pieces with particular reference to the files stored according to the MIDI standards. This method is based on the quantification of each string by calculating its entropy. It is an empirical methodology that provides results expressed in numbers that may be analyzed. This enables a comparison between two strings of different length highlighting their potential identity (sameness), similarity and homology. The representation by means of an isometric diagram accommodates a better interpretation of the results. The effectiveness of the proposed melodic representations and algorithms is tested against a series of melodic examples.