Measuring musical rhythm similarity

Edit distance versus minimum-weight many-to-many matchings

Godfried Toussaint, Seung Man Oh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Musical rhythms are represented as binary symbol sequences of sounded and silent pulses of unit-duration. A measure of distance (dissimilarity) between a pair of rhythms commonly used in music information retrieval, music perception, and musicology is the edit (Levenshtein) distance, defined as the minimum number of symbol insertions, deletions, and substitutions needed to transform one rhythm into the other. A measure of distance often used in object recognition is the minimum-weight many-to-many matching distance between the object’s features. These two approaches are compared empirically, in terms of how well they predict human judgments of musical rhythm similarity, using a real-world family of Middle-Eastern rhythms.

Original languageEnglish (US)
Title of host publicationProceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016
EditorsAshu M.G. Solo, Fernando G. Tinetti, Hamid R. Arabnia, Peter M. LaMonica, Elena B. Kozerenko, Todd Waskiewicz, George Jandieri, David de la Fuente, Raymond A. Liuzzi, Jose A. Olivas, Roger Dziegiel
PublisherCSREA Press
Pages186-189
Number of pages4
ISBN (Electronic)1601324383, 9781601324382
StatePublished - Jan 1 2016
Event2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016 - Las Vegas, United States
Duration: Jul 25 2016Jul 28 2016

Publication series

NameProceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016

Conference

Conference2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016
CountryUnited States
CityLas Vegas
Period7/25/167/28/16

Fingerprint

Object recognition
Information retrieval
Substitution reactions

Keywords

  • Edit distance
  • Hungarian algorithm
  • Many-to-many matchings
  • Musical rhythm
  • Perception
  • Similarity measures

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

Toussaint, G., & Oh, S. M. (2016). Measuring musical rhythm similarity: Edit distance versus minimum-weight many-to-many matchings. In A. M. G. Solo, F. G. Tinetti, H. R. Arabnia, P. M. LaMonica, E. B. Kozerenko, T. Waskiewicz, G. Jandieri, D. de la Fuente, R. A. Liuzzi, J. A. Olivas, ... R. Dziegiel (Eds.), Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016 (pp. 186-189). (Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016). CSREA Press.

Measuring musical rhythm similarity : Edit distance versus minimum-weight many-to-many matchings. / Toussaint, Godfried; Oh, Seung Man.

Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016. ed. / Ashu M.G. Solo; Fernando G. Tinetti; Hamid R. Arabnia; Peter M. LaMonica; Elena B. Kozerenko; Todd Waskiewicz; George Jandieri; David de la Fuente; Raymond A. Liuzzi; Jose A. Olivas; Roger Dziegiel. CSREA Press, 2016. p. 186-189 (Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Toussaint, G & Oh, SM 2016, Measuring musical rhythm similarity: Edit distance versus minimum-weight many-to-many matchings. in AMG Solo, FG Tinetti, HR Arabnia, PM LaMonica, EB Kozerenko, T Waskiewicz, G Jandieri, D de la Fuente, RA Liuzzi, JA Olivas & R Dziegiel (eds), Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016. Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016, CSREA Press, pp. 186-189, 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016, Las Vegas, United States, 7/25/16.
Toussaint G, Oh SM. Measuring musical rhythm similarity: Edit distance versus minimum-weight many-to-many matchings. In Solo AMG, Tinetti FG, Arabnia HR, LaMonica PM, Kozerenko EB, Waskiewicz T, Jandieri G, de la Fuente D, Liuzzi RA, Olivas JA, Dziegiel R, editors, Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016. CSREA Press. 2016. p. 186-189. (Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016).
Toussaint, Godfried ; Oh, Seung Man. / Measuring musical rhythm similarity : Edit distance versus minimum-weight many-to-many matchings. Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016. editor / Ashu M.G. Solo ; Fernando G. Tinetti ; Hamid R. Arabnia ; Peter M. LaMonica ; Elena B. Kozerenko ; Todd Waskiewicz ; George Jandieri ; David de la Fuente ; Raymond A. Liuzzi ; Jose A. Olivas ; Roger Dziegiel. CSREA Press, 2016. pp. 186-189 (Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016).
@inproceedings{ca00304a893147509af2ddaecbdda1a1,
title = "Measuring musical rhythm similarity: Edit distance versus minimum-weight many-to-many matchings",
abstract = "Musical rhythms are represented as binary symbol sequences of sounded and silent pulses of unit-duration. A measure of distance (dissimilarity) between a pair of rhythms commonly used in music information retrieval, music perception, and musicology is the edit (Levenshtein) distance, defined as the minimum number of symbol insertions, deletions, and substitutions needed to transform one rhythm into the other. A measure of distance often used in object recognition is the minimum-weight many-to-many matching distance between the object’s features. These two approaches are compared empirically, in terms of how well they predict human judgments of musical rhythm similarity, using a real-world family of Middle-Eastern rhythms.",
keywords = "Edit distance, Hungarian algorithm, Many-to-many matchings, Musical rhythm, Perception, Similarity measures",
author = "Godfried Toussaint and Oh, {Seung Man}",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
series = "Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016",
publisher = "CSREA Press",
pages = "186--189",
editor = "Solo, {Ashu M.G.} and Tinetti, {Fernando G.} and Arabnia, {Hamid R.} and LaMonica, {Peter M.} and Kozerenko, {Elena B.} and Todd Waskiewicz and George Jandieri and {de la Fuente}, David and Liuzzi, {Raymond A.} and Olivas, {Jose A.} and Roger Dziegiel",
booktitle = "Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016",

}

TY - GEN

T1 - Measuring musical rhythm similarity

T2 - Edit distance versus minimum-weight many-to-many matchings

AU - Toussaint, Godfried

AU - Oh, Seung Man

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Musical rhythms are represented as binary symbol sequences of sounded and silent pulses of unit-duration. A measure of distance (dissimilarity) between a pair of rhythms commonly used in music information retrieval, music perception, and musicology is the edit (Levenshtein) distance, defined as the minimum number of symbol insertions, deletions, and substitutions needed to transform one rhythm into the other. A measure of distance often used in object recognition is the minimum-weight many-to-many matching distance between the object’s features. These two approaches are compared empirically, in terms of how well they predict human judgments of musical rhythm similarity, using a real-world family of Middle-Eastern rhythms.

AB - Musical rhythms are represented as binary symbol sequences of sounded and silent pulses of unit-duration. A measure of distance (dissimilarity) between a pair of rhythms commonly used in music information retrieval, music perception, and musicology is the edit (Levenshtein) distance, defined as the minimum number of symbol insertions, deletions, and substitutions needed to transform one rhythm into the other. A measure of distance often used in object recognition is the minimum-weight many-to-many matching distance between the object’s features. These two approaches are compared empirically, in terms of how well they predict human judgments of musical rhythm similarity, using a real-world family of Middle-Eastern rhythms.

KW - Edit distance

KW - Hungarian algorithm

KW - Many-to-many matchings

KW - Musical rhythm

KW - Perception

KW - Similarity measures

UR - http://www.scopus.com/inward/record.url?scp=85068320039&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068320039&partnerID=8YFLogxK

M3 - Conference contribution

T3 - Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016

SP - 186

EP - 189

BT - Proceedings of the 2016 International Conference on Artificial Intelligence, ICAI 2016 - WORLDCOMP 2016

A2 - Solo, Ashu M.G.

A2 - Tinetti, Fernando G.

A2 - Arabnia, Hamid R.

A2 - LaMonica, Peter M.

A2 - Kozerenko, Elena B.

A2 - Waskiewicz, Todd

A2 - Jandieri, George

A2 - de la Fuente, David

A2 - Liuzzi, Raymond A.

A2 - Olivas, Jose A.

A2 - Dziegiel, Roger

PB - CSREA Press

ER -