Measuring Musical Rhythm Similarity - Statistical Features versus Transformation Methods

Two approaches to measuring the similarity between symbolically notated musical rhythms are compared with each other and with human judgments of perceived similarity. The first is the edit-distance, a popular transformation method, applied to the symbolic rhythm sequences. The second approach employs the histograms of the inter-onset-intervals (IOIs) calculated from the rhythms. Furthermore, two methods for dealing with the histograms are also compared. The first utilizes the Mallows distance, a transformation method akin to the Earth-Movers distance popular in computer vision, and the second extracts a group of standard statistical features, used in music information retrieval, from the IOI-histograms. The measures are compared using four contrastive musical rhythm data sets by means of statistical Mantel tests that compute correlation coefficients between the various dissimilarity matrices. The results provide evidence from the aural domain, that transformation methods such as the edit distance are superior to feature-based methods for predicting human judgments of similarity. The evidence also supports the hypothesis that IOI-histogram-based methods are better than music-theoretical structural features computed from the rhythms themselves, provided that the rhythms do not share identical IOI histograms.

[1]  R. Shepard.  Stimulus and response generalization: A stochastic model relating generalization to distance in psychological space , 1957 .

[2]  Sung-Hyuk Cha,et al.  On measuring the distance between histograms , 2002, Pattern Recognit..

[3]  Godfried T. Toussaint,et al.  The Geometry of Musical Rhythm , 2013, JCDCG.

[4]  N. Chater,et al.  Similarity as transformation , 2003, Cognition.

[5]  Tan Hakan Özaslan,et al.  Note Onset Deviations as Musical Piece Signatures , 2013, PloS one.

[6]  Marjorie Senechal.  A point set puzzle revisited , 2008, Eur. J. Comb..

[7]  A. Tversky.  Features of Similarity , 1977 .

[8]  Godfried T. Toussaint,et al.  The Edit Distance as a Measure of Perceived Rhythmic Similarity , 2011 .

[9]  Godfried T. Toussaint,et al.  Measuring musical rhythm similarity : Transformation versus feature-based methods , 2013 .

[10]  V. Sloutsky.  The role of similarity in the development of categorization , 2003, Trends in Cognitive Sciences.

[11]  Alberto Sanfeliu,et al.  Signatures versus histograms: Definitions, distances and algorithms , 2006, Pattern Recognit..

[12]  Yves Van de Peer,et al.  zt: A Sofware Tool for Simple and Partial Mantel Tests , 2002 .

[13]  N Mantel,et al.  A technique of nonparametric multivariate analysis. , 1970, Biometrics.

[14]  G. Toussaint.  The Pairwise Variability Index as a Tool in Musical Rhythm Analysis , 2012 .

[15]  Robert A. Wagner,et al.  An Extension of the String-to-String Correction Problem , 1975, JACM.

[16]  Séverine Dubuisson,et al.  Tree-structured image difference for fast histogram and distance between histograms computation , 2011, Pattern Recognit. Lett..

[17]  Peter J. Bickel,et al.  The Earth Mover's distance is the Mallows distance: some insights from statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[18]  A. L. Patterson.  Ambiguities in the X-Ray Analysis of Crystal Structures , 1944 .

[19]  Gerhard Widmer,et al.  Evaluating Rhythmic descriptors for Musical Genre Classification , 2004 .

[20]  Godfried T. Toussaint Malcolm Campbell Naor Brown.  Computational Models of Symbolic Rhythm Similarity: Correlation with Human Judgments , 2011 .

[21]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[22]  Xiaodong Gu,et al.  Histogram similarity measure using variable bin size distance , 2010, Comput. Vis. Image Underst..

[23]  N. Chater,et al.  Transformation and alignment in similarity , 2009, Cognition.

[24]  Daniel H. Huson,et al.  SplitsTree: analyzing and visualizing evolutionary data , 1998, Bioinform..