David Garfinkle
ABSTRACT
Content-Based Music Retrieval (CBMR) for symbolic music aims to find all similar occurrences of a musical pattern within a larger database of symbolic music. To the best of our knowledge there does not currently exist a distributable CBMR software package integrated with a music analysis toolkit that facilitates extendability with new CBMR methods. This project presents a new MIR tool called "PatternFinder" satisfying these goals. PatternFinder is built with the computational musicology Python package music21, which provides a flexible platform capable of working with many music notation formats. To achieve polyphonic CBMR, we implement seven geometric algorithms developed at the University of Helsinki---four of which are being implemented and released publicly for the first time. The application of our MIR tool is then demonstrated through a musicological investigation of Renaissance imitation masses, which borrow melodic or contrapuntal material from a pre-existing musical work. In addition, we show Pattern-Finder's ability to find a contrapuntal pattern over a large dataset, Palestrina's 104 masses. Our investigations demonstrate the relevance of our tool for musicological research as well as its potential application for locating music within digital music libraries.
- Michael Scott Cuthbert and Christopher Ariza. 2010. music21: A toolkit for computer-aided musicology and symbolic music data. In Proceedings of the 11th International Society for Music Information Retrieval Conference. 637--642.Google Scholar
- David Rizo. 2010. Symbolic music comparison with tree data structures. PhD. Dissertation. Universidad de Alicante.Google Scholar
- J Stephen Downie. 1999. Evaluating a simple approach to music information retrieval: conceiving melodic n-grams as text. Ph.D. Dissertation.Google Scholar
- David Huron. 1995. The Humdrum toolkit: reference manual. Technical Report.Google Scholar
- Berit Janssen, Peter van Kranenburg, and Anja Volk. 2015. A comparison of symbolic similarity measures for finding occurrences of melodic segments. In Proceedings of the 16th International Society for Music Information Retrieval Conference. Malaga, Spain, 659--665.Google Scholar
- Kjell Lemstrom. 2000. String matching techniques for music retrieval. PhD. Dissertation. University of Helsinki.Google Scholar
- Antti Laaksonen. 2013. Efficient and simple algorithms for time-scaled and time-warped music search. In Proceedings of the 10th International Symposium on Computer Music Multidisciplinary Research. Laboratoire de Mécanique et d'Acoustique, Marseille, France, 621--630.Google Scholar
- Kjell Lemström. 2010. Towards more robust geometric content-based music retrieval. In Proceedings of the 11th International Society for Music Information Retrieval Conference, J. Stephen Downie and Remco C. Veltkamp (Eds.). Utrecht, Netherlands, 577--582.Google Scholar
- Kjell Lemström and Mika Laitinen. 2011. Transposition and time-warp invariant geometric music retrieval algorithms. In Proceedings of 2011 IEEE International Conference on Multimedia and Expo. Google ScholarDigital Library
- Marcelle Lessoil-Daelman. 2002. Une approche synoptique des motifs et des modules dans la messe parodique. PhD. Dissertation. McGill University.Google Scholar
- Honey Meconi (Ed.). 2003. Early musical borrowing. Taylor & Francis.Google Scholar
- Marcel Mongeau and David Sankoff. 1990. Comparison of musical sequences. Computers and the Humanities 24, 3 (1990), 161--175. Google Scholar
- Daniel Müllensiefen and Klaus Frieler. 2009. The Simile algorithms documentation 0. 3. Technical Report. Goldsmiths College, University of London, London.Google Scholar
- Peter Schubert. 2007. Hidden forms in Palestrina's first book of four-voice motets. Journal of the American Musicological Society 60, 3 (2007), 483--556. Google ScholarCross Ref
- Albert Pinto and Paolo Tagliolato. 2008. A generalized graph-spectral approach to melodic modeling and retrieval. In Proceedings of the 1st ACM International Conference on Multimedia Information Retrieval. New York, NY, USA, 89--96. Google ScholarDigital Library
- David Rizo, José Manuel Iñesta, and Kjell Lemström. 2011. Polyphonic music retrieval with classifier ensembles. Journal of New Music Research 40, 4 (2011), 313--324. Google ScholarCross Ref
- Christian André Romming and Eleanor Selfridge-Field. 2007. Algorithms for polyphonic music retrieval: the hausdorff metric and geometric hashing. In Proceedings of International Society for Music Information Retrieval Conference (ISMIR 2007). 457--462.Google Scholar
- Peter Schubert and Marcelle Lessoil-Daelman. 2013. What modular analysis can tell us about musical modeling in the renaissance. Music Theory Online 19, 1 (2013).Google Scholar
- Rainer Typke. 2007. Music retrieval based on melodic similarity. PhD dissertation. Utrecht University, Netherlands.Google Scholar
- Esko Ukkonen, Kjell Lemström, and Veli Mäkinen. 2003. Geometric algorithms for transposition invariant content-based music retrieval. In Proceedings of the Fourth International Conference on Music Information Retrieval. Baltimore, Maryland, USA, 193--199.Google Scholar
- Julián Urbano, Juan Lloréns, Jorge Morato, and Sonia Sánchez-Cuadrado. 2011. Melodic similarity through shape similarity. In Lecture Notes in Computer Science. Vol. 6684. 338--355. Google ScholarCross Ref
- Valerio Velardo, Mauro Vallati, and Steven Jan. 2016. Symbolic melodic similarity: state of the art and future challenges. Computer Music Journal 40, 2 (2016), 70--83. Google ScholarDigital Library
- Pietro Cerone. El Melopeo y Maestro, 1613. Excerpt translated in Oliver Strunk, Source readings in music history from classical antiquity through the romantic era, 1950. W.W. Norton & Company, Inc., New York, 265--68.Google Scholar
Index Terms
- PatternFinder: Content-Based Music Retrieval with music21
Recommendations
Music scale modeling for melody matching
MULTIMEDIA '03: Proceedings of the eleventh ACM international conference on MultimediaSeveral time series matching techniques have been proposed for content-based music retrieval. These techniques have shown to be robust and effective for music retrieval by acoustic inputs, such as query-by-humming. However, due to the key transposition ...
Effective Music Retrieval by Sequential Pattern-Based Alignment
TAAI '12: Proceedings of the 2012 Conference on Technologies and Applications of Artificial IntelligenceDue to the rapid growth of music data, how to effectively and efficiently retrieve the interested music piece has been an attractive issue in recent years. In traditional music retrieval systems, the most popular way is to retrieve the music piece by ...
A unified approach to content-based and fault-tolerant music recognition
In this paper, we propose a unified approach to fast index-based music recognition. As an important area within the field of music information retrieval (MIR), the goal of music recognition is, given a database of musical pieces and a query document, to ...
Comments