Tune plagiarism in pop music is a common and often feverishly debated phenomenon which surely has to do with the vast amounts of money that individual melodies are able to generate in today's pop music business. The similarity between melodies is assumed to be a very important factor in a court's decision about whether a new tune is an illegitimate version of a pre-existing melody. Despite the wide-spread belief that there is a fixed and simple limit to the number of corresponding notes between two melodies, actual court decisions are based on far more complex considerations regarding the musical material.
This paper first sketches the legal framework and principal features of the legal processing of cases of alleged melodic plagiarism with a focus on US copyright law and discusses selected cases to highlight the corresponding legal practices. In the empirical part of this paper, we model court decisions for cases of alleged melodic plagiarism employing a number of similarity algorithms. As a ground truth dataset we use a collection of 20 publicly available cases from the last 30 years of US jurisdiction. We compare the performance of standard similarity algorithms (edit distance and n-gram similarity measures) to several new similarity algorithms that make use of statistical information about the prevalence of chains of pitch intervals in a large pop music database. Results indicate that these statistically informed algorithms generally outperform the comparison algorithms. In particular, algorithms based on Tversky's (1977) concept of similarity show a high performance of up to 90% of court decisions correctly predicted. We discuss the performance and structure of the algorithms in relation to a few interesting example cases and give an outlook on the potential and intricacies of our approach.
AhlbäckS. (2007). Melodic similarity as a determinant of melody structure. Musicæ Scientiæ, Discussion Forum 4A, 235–80.
2.
AloupisG., FevensT., LangermanS., MatsuiT., MesaA., RappaportD., & ToussaintG. (2003). Computing the similarity of two melodies. In Proceedings of the 15th Canadian Conference on Computational Geometry, Halifax, Canada: Dalhousie University, 81–4.
3.
BaayenH. (2001). Word frequency distributions.Dordrecht: Kluwer.
4.
BGH [German Federal Court of Justice] (1988a). “Fantasy”. In Gewerblicher Rechtsschutz und Urheberrecht (GRUR) 11/1988, 810–12.
5.
BGH [German Federal Court of Justice] (1988b). “Ein bißchen Frieden”. In Gewerblicher Rechtsschutz und Urheberrecht (GRUR) 11/1988, 812–16.
6.
CanisiusC. (1992). Beethoven. Sehnsucht und Unruhe in der Musik. Aspekte zu Leben und Werk. Serie Musik Bd. 8297. München: Piper.
7.
Columbia Law School & UCLA Law Copyright Infringement Project. Edited by Charles Cronin et al. Launched 2002. Update 5/2008. URL: http://cip.law.ucla.edu/
8.
ConklinD., & AnagnostopoulouC. (2006). Segmental pattern discovery in music. Informs Journal on Computing, 18(3), 285–93.
9.
CrawfordT., IliopoulosC.S., & RamanR. (1998). String-Matching techniques for musical similarity and melodic recognition. In HewlettW.B., & Selfridge-FieldE. (eds), Melodic similarity. Concepts, procedures, and applications. Computing in Musicology11. Cambridge, MA: MIT Press, 73–100.
10.
CroninC. (1998). Concepts of melodic similarity in music-copyright infringement suits. In HewlettW.B., & Selfridge-FieldE. (eds), Melodic similarity. Concepts, procedures, and applications. Computing in Musicology11. Cambridge, MA: MIT Press, 187–209.
11.
DannenbergR.B., BirminghamW.P., TzanetakisG., MeekC., HuN., & PardoB. (2004). The MUSART Testbed for Query-By-Humming Evaluation. Computer Music Journal28(2), 34–48.
12.
DownieJ.S. (1999). Evaluating a simple approach to music information retrieval. Conceiving melodic n-grams as text. PhD Thesis, University of Western Ontario, London (Ontario), Canada. URL: http://music-ir.org/~jdownie/downie_thesis.pdf.
EerolaT., HimbergT., ToiviainenP., & LouhivuoriJ. (2006). Perceived complexity of Western and African folk melodies by Western and African listeners. Psychology of Music, 34(3), 341–75.
15.
EerolaT., & BregmanM. (2007). Melodic and contextual similarity of folk song phrases. Musicæ Scientiæ, Discussion Forum 4A, 211–33.
16.
Fred Fisher vs. Dillingham, 298 F. 145 (1924). Source: Columbia Law School & UCLA Law Copyright Infringement Project. Edited by Charles Cronin et al Launched 2002. Update 5/2008. URL: http://cip.law.ucla.edu/cases/case_fisherdill.html
17.
FrielerK., & MüllensiefenD. (2007). Melodic similarity: The big picture and some new ideas. Presentation given at the MIR Symposium and Workshop, 20th Feb. 2007, University of Utrecht. URL: http://www.cs.uu.nl/research/projects/witchcraft/mir2007/
18.
GrachtenM., ArcosJ. Ll., & López de MántarasR. (2004). Melodic similarity: Looking for a good abstraction level. Proceedings of the 5th International Conference on Music Information Retrieval. Pompeu Fabra University, Barcelona, Spain. URL: http://waits.cp.jku.at/~maarten/articles/GrachtenArcosMantaras-ISMIR04.pdf
GusfieldD. (1997). Algorithms on Strings, Trees, and Sequences: Computer Science and Computational Biology.Cambridge, UK: Cambridge University Press.
21.
HandD.J. (1997). Construction and assessment of classification rules.Chichester: Wiley.
22.
GuoA., & SigelmannH. (2004). Time-warped longest common subsequence algorithm for music retrieval. Proceedings of the 5th International Conference on Music Information Retrieval. Pompeu Fabra University, Barcelona, Spain. URL: http://ismir2004.ismir.net/proceedings/p049-page-258-paper113.pdf.
23.
HowardJ. (1998). Strategies for sorting musical incipits. In HewlettW.B., & Selfridge-FieldE. (eds), Melodic similarity. Concepts, procedures, and applications. Computing in Musicology11. Cambridge, MA: MIT Press, 119–28.
24.
JörgerT. (1992). Das Plagiat in der Popularmusik…Baden-Baden: Nomos.
25.
JurafskyD., & MartinJ.H. (2000). Speech and language processing: An introduction to natural language processing, computational linguistics, and speech recognition.Upper Saddle River (NJ): Prentice Hall.
26.
KlugeR. (1974). Faktorenanalytische Typenbestimmung an Volksliedmelodien.Leipzig: VEB Deutscher Verlag für Musik.
27.
LartillotO., & ToiviainenP. (2007). Motivic matching strategies for automated pattern extraction. Musicæ Scientiæ, Discussion Forum 4A, 281–314.
28.
LemströmK., NavarroG., & PinzonY. (2005). Practical algorithms for transposition-invariant string-matching, Journal of Discrete Algorithms, 3(2-4), Combinatorial Pattern Matching (CPM) Special Issue, 267–92.
29.
ManningC., & SchützeH. (1999). Foundations of statistical natural language Processing.Cambridge, MA: MIT Press.
30.
McJohnS. (2006). Copyright: Examples and explanations.New York: Aspen.
31.
McNabR.J., SmithL.A., WittenI.H., HendersonC.L., & CunninghamS.J. (1996). Towards the digital music library: Tune retrieval from acoustic input. In Digital Libraries ‘96. Proceedings ACM Digital Libraries Conference, 11–18.
32.
MeekC., & BirminghamW. (2002). Johnny Can't Sing. A comprehensive error model for sung music queries. In FingerhutM. (ed), Proceedings of the Third International Conference on Music Information Retrieval. Paris: IRCAM, 124–32.
33.
MongeauM., & SankoffD. (1990). Comparison of musical sequences. Computers and the Humanities24, 161–75.
34.
MüllensiefenD. (2006). “Exact measures of musical structure for predicting memory for melodies”. In M. Baroni, A. R. Addessi, R. Caterina, & M. Costa (eds), Proceedings of the 9th international conference of music perception and cognition (ICMPC9), 782–90.
35.
MüllensiefenD., & FrielerK. (2004). Cognitive Adequacy in the Measurement of Melodic similarity: Algorithmic vs. human judgments. Computing in Musicology13, 147–76.
MüllensiefenD., WigginsG., & LewisD. (2008). High-level feature descriptors and corpus-based musicology: Techniques for modelling music cognition. In SchneiderA. (ed), Hamburger Jahrbuch für Musikwissenschaft, 23. Frankfurt: Peter Lang, 133–55.
38.
Ó'MaidínD. (1998). A geometrical algorithm for melodic difference in melodic similarity. In HewlettW.B., & Selfridge-FieldE. (eds), Melodic similarity. Concepts, procedures, and a Applications. Computing in Musicology11. Cambridge, MA: MIT Press, 65–72.
39.
NettheimN. (1998). Melodic pattern-detection using MuSearch in Schubert's Die schöne Müllerin. In HewlettW.B., & Selfridge-FieldE. (eds), Melodic similarity. Concepts, procedures, and applications. Computing in Musicology11. Cambridge, MA: MIT Press, 159–68.
40.
PatryW. F. (1994). Copyright law and practise. Library of Congress Cataloging-in-Publication Data. Bureau of National Affairs, Inc.Washington, D. C.
41.
PendzichM. (2004). Von der Coverversion zum Hit-Recycling. Historische, ökonomische und rechtliche Aspekte eines zentralen Phänomens der Pop- und Rockmusik.2nd Ed. 2008. Münster: LIT.
42.
RizoD., LemströmK., & IñestaJ.M. (2008). Tree structured and combined methods for comparing metered polyphonic music. In Proceedings Computer Music Modeling and Retrieval 2008 (CMMR'08), Copenhagen, Denmark, 263–78.
ShannonC.E. (1948). A mathematical theory of communication. Bell System Technical Journal27, 379–423.
45.
SoocherS. (1999). They fought the law. Rock music goes to court.New York: Schirmer.
46.
SteinbeckW. (1982). Struktur und Ähnlichkeit. Methoden automatisierter Melodieanalyse. Kieler Schriften zur Musikwissenschaft XXV.Kassel: Bärenreiter.
47.
SwetsJ.A. (1973). The relative operating characteristic in psychology. Science182, 990–1000.
48.
TverskyA. (1977). Features of similarity. Psychological Review, 84, 327–52.
49.
TypkeR., WieringF., & VeltkampR. C. (2007). Transportation distances in human perception of melodic similarity. Musicæ Scientiæ, Discussion Forum 4A, 153–81.
UnalE., ChewE., GeorgiouP. G., & NarayananS. S. (2008). Challenging uncertainty in query by humming systems: A fingerprinting approach. IEEE Transactions on Audio Speech, and Language Processing, 16(2), 359–71.
52.
WeydeT. (2004). Modeling rhythmic motif structure with fuzzy logic and machine learning. In HewlettW.B., & Selfridge-FieldE. (eds), Music query. Methods, models, and user studies. Computing in Musicology, 13. Cambridge, MA: MIT Press, 35–50.
WieringF., TypkeR., & VeltkampR. (2004). Transportation distances and their application in music-notation retrieval. In HewlettW.B., & Selfridge-FieldE. (eds), Music query. Methods, models, and user studies. Computing in Musicology13. Cambridge, MA: MIT Press, 113–28.
55.
WigginsG.A., PearceM., & MüllensiefenD. (2009). Computation al modelling of music cognition and musical creativity. In DeanR. (ed), Oxford Handbook of Computer Music and Digital Sound Culture. Oxford: University Press (in press).
