Towards a Computational Model of Melody Identification in Polyphonic Music

This paper presents first steps towards a simple, robust computational model of automatic melody identification. Based on results from music psychology that indicate a relationship between melodic complexity and a listener's attention, we postulate a relationship between musical complexity and the probability of a musical line to be perceived as the melody. We introduce a simple measure of melodic complexity, present an algorithm for predicting the most likely melody note at any point in a piece, and show experimentally that this simple approach works surprisingly well in rather complex music.

[1]  E. Narmour.  The analysis and cognition of basic melodic structures , 1992 .

[2]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[3]  I. Shmulevich,et al.  Measures of Temporal Pattern Complexity , 2000 .

[4]  Andranick Tanguiane.  Artificial Perception and Music Recognition , 1993, Lecture Notes in Computer Science.

[5]  Olivier Lartillot,et al.  A Musical Pattern Discovery System Founded on a Modeling of Listening Strategies , 2004, Computer Music Journal.

[6]  Sang Joon Kim,et al.  A Mathematical Theory of Communication , 2006 .

[7]  Andranik S. Tangiuane.  Artificial Perception and Music Recognition , 1993 .

[8]  Gerhard Widmer,et al.  Separating voices in MIDI , 2006, ISMIR.

[9]  Tillman Weyde,et al.  Efficient Melody Retrieval with Motif Contour Classes , 2005, ISMIR.

[10]  B. Snyder.  Music and Memory: An Introduction , 2001 .

[11]  Justin Zobel,et al.  Manipulation of music for melody matching , 1998, MULTIMEDIA '98.

[12]  Stephen McAdams,et al.  Structural and affective aspects of music from statistical audio signal analysis , 2006, J. Assoc. Inf. Sci. Technol..

[13]  S. McAdams,et al.  Structural and affective aspects of music from statistical audio signal analysis: Special Topic Section on Computational Analysis of Style , 2006 .

[14]  Ming Li,et al.  Genre Classification via an LZ78-Based String Kernel , 2005, ISMIR.

[15]  Darrell Conklin,et al.  Melodic analysis with segment classes , 2006, Machine Learning.

[16]  C. Stevens,et al.  Sweet Anticipation: Music and the Psychology of Expectation, by David Huron . Cambridge, Massachusetts: MIT Press, 2006 , 2007 .

[17]  Abraham Lempel,et al.  A universal algorithm for sequential data compression , 1977, IEEE Trans. Inf. Theory.

[18]  David Rizo,et al.  Melodic track identification in MIDI files , 2006 .

[19]  H. Grosser.  Chicago , 1906 .

[20]  J. Davenport.  Editor , 1960 .

[21]  A. Gabrielsson.  The Performance of Music , 1999 .

[22]  Roger B. Dannenberg,et al.  Query by humming with the VocalSearch system , 2006, CACM.