Symbolic Music Similarity through a Graph-Based Representation

In this work, a novel representation system for symbolic music is described. The proposed representation system is graph-based and could theoretically represent music both from a horizontal (contrapuntal) and from a vertical (harmonic) point of view, by keeping into account contextual and harmonic information. It could also include relationships between internal variations of motifs and themes. This is achieved by gradually simplifying the melodies and generating layers of reductions that include only the most important notes from a structural and harmonic viewpoint. This representation system has been tested in a music information retrieval task, namely melodic similarity, and compared to another system that performs the same task but does not consider any contextual or harmonic information, showing how the structural information is needed in order to find certain relations between musical pieces. Moreover, a new dataset consisting of more than 5000 leadsheets is presented, with additional meta-musical information taken from different web databases, including author, year of first performance, lyrics, genre and stylistic tags.

[1]  Emilios Cambouropoulos,et al.  A general pitch interval representation: Theory and applications , 1996 .

[2]  Emilios Cambouropoulos,et al.  The Local Boundary Detection Model (LBDM) and its Application in the Study of Expressive Timing , 2001, ICMC.

[3]  Hugues Vinet,et al.  The Representation Levels of Music Information , 2003, CMMR.

[4]  Mark B. Sandler,et al.  Symbolic Representation of Musical Chords: A Proposed Syntax for Text Annotations , 2005, ISMIR.

[5]  José Manuel Iñesta Quereda,et al.  Tree Model of Symbolic Music for Tonality Guessing , 2006, Artificial Intelligence and Applications.

[6]  Ichiro Fujinaga,et al.  jSymbolic: A Feature Extractor for MIDI Files , 2006, ICMC.

[7]  M. Fatih Demirci,et al.  Indexing Music Collections Through Graph Spectra , 2007, ISMIR.

[8]  Nicola Orio,et al.  A Measure of Melodic Similarity based on a Graph Representation of the Music Structure , 2009, ISMIR.

[9]  W. Bruce Croft,et al.  Search Engines - Information Retrieval in Practice , 2009 .

[10]  Alan Marsden.  Recognition of Variations Using Automatic Schenkerian Reduction , 2010, ISMIR.

[11]  Pierre Hanna,et al.  A Survey Of Chord Distances With Comparison For Chord Analysis , 2010, ICMC.

[12]  C. Krumhansl,et al.  A Theory of Tonal Hierarchies in Music , 2010 .

[13]  Christopher Ariza,et al.  Music21: A Toolkit for Computer-Aided Musicology and Symbolic Music Data , 2010, ISMIR.

[14]  David Rizo Valero.  Symbolic music comparison with tree data structures , 2011 .

[15]  François Pachet,et al.  A Comprehensive Online Database of Machine-Readable Lead-Sheets for Jazz Standards , 2013, ISMIR.

[16]  Maximos A. Kaliakatsos-Papakostas,et al.  An Idiom-independent Representation of Chords for Computational Music Analysis and Generation , 2014, ICMC.

[17]  Julián Urbano.  MelodyShape at MIREX 2014 Symbolic Melodic Similarity , 2014 .

[18]  A. Volk,et al.  Automatic Segmentation of Symbolic Music Encodings: A Survey , 2015 .

[19]  Julián Urbano.  MelodyShape: a Library and Tool for Symbolic Melodic Similarity based on Shape Similarity , 2015 .

[20]  Matthias Abend.  Cognitive Foundations Of Musical Pitch , 2016 .

[21]  Satoshi Tojo,et al.  Implementing Methods for Analysing Music Based on Lerdahl and Jackendoff's Generative Theory of Tonal Music , 2016, Computational Music Analysis.

[22]  Emilios Cambouropoulos,et al.  The Harmonic Musical Surface and Two Novel Chord Representation Schemes , 2016, Computational Music Analysis.

[23]  Tillman Weyde,et al.  A Wavelet-Based Approach to Pattern Discovery in Melodies , 2016, Computational Music Analysis.