ABSTRACT
Rhythmic similarity, a fundamental task within Music Information Retrieval, has recently been applied in creative music contexts to retrieve musical audio or guide audio-content transformations. However, there is still very little knowledge of the typical rhythmic similarity values between overlapping musical structures per instrument, genre, and time scales, which we denote as rhythmic compatibility. This research provides the first steps towards the understanding of rhythmic compatibility from the systematic analysis of MedleyDB, a large multi-track musical database composed and performed by artists. We apply computational methods to compare database stems using representative rhythmic similarity metrics – Rhythmic Histogram (RH) and Beat Spectrum (BS) – per genre and instrumental families and to understand whether RH and BS are prone to discriminate genres at different time scales. Our results suggest that 1) rhythmic compatibility values lie between [.002,.354] (RH) and [.1,.881] (BS), 2) RH outperforms BS in discriminating genres, and 3) different time scale in RH and BS impose significant differences in rhythmic compatibility.
- Adam Berenzweig, Beth Logan, Daniel P.W. Ellis, and Brian Whitman. 2004. A Large-Scale Evaluation of Acoustic and Subjective Music-Similarity Measures. Computer Music Journal 28, 2 (2004), 63–76.Google ScholarDigital Library
- Rachel Bittner, Justin Salamon, Mike Tierney, Matthias Mauch, Chris Cannam, and Juan Bello. 2014. MedleyDB: A Multitrack Dataset for Annotation-Intensive MIR Research. In Proc. 15th ISMIR. 155–160.Google Scholar
- Rachel Bittner, Justin Salamon, Mike Tierney, Matthias Mauch, Chris Cannam, and Juan Bello. 2014. MedleyDB Instrument Taxonomy. https://github.com/marl/medleydb/blob/master/medleydb/resources/taxonomy.yaml.Google Scholar
- F Alton Everest and Ken C Pohlmann. 2015. Master Handbook of Acoustics, Sixth Edition (6th ed. ed.). McGraw-Hill Education, New York.Google Scholar
- Arthur Flexer. 2014. On Inter-rater Agreement in Audio Music Similarity. In Proc. 15th ISMIR. Taipei, Taiwan, 245–250.Google Scholar
- J. Foote and Shingo Uchihashi. 2001. The beat spectrum: a new approach to rhythm analysis. In IEEE Int. Conf. on Multimedia and Expo (ICME). IEEE, Tokyo, JP, 881–884.Google ScholarCross Ref
- Masataka Goto. 2012. Grand Challenges in Music Information Research. In Multimodal Music Processing, Meinard Müller, Masataka Goto, and Markus Schedl(Eds.). Dagstuhl Follow-Ups, Vol. 3. Schloss Dagstuhl–Leibniz-Zentrum fuer Informatik, Dagstuhl, Germany, 217–226.Google Scholar
- Garth Griffin, Youngmoo E. Kim, and Douglas Turnbull. 2010. Beat-Sync-Mash-Coder: A web application for real-time creation of beat-synchronous music mashups. In IEEE ICASSP. IEEE, Dallas, USA, 437–440.Google Scholar
- TU Wien MIR Group. 2015. Rhythm Pattern Audio Feature Extractor for Music Similarity, Classification and Recommendation. https://github.com/tuwien-musicir/rp_extract.Google Scholar
- Peter Knees and Markus Schedl. 2013. A Survey of Music Similarity and Recommendation from Music Context Data. ACM Trans. Multimedia Comput. Commun. Appl. 10, 1 (2013), 21 pages.Google ScholarDigital Library
- Thomas Lidy. 2006. Evaluation of New Audio Features and Their Utilization in Novel Music Retrieval Applications. Ph.D. Dissertation.Google Scholar
- Thomas Lidy and Andreas Rauber. 2005. Evaluation of Feature Extractors and Psycho-Acoustic Transformations for Music Genre Classification. In Proc. 6th ISMIR. ISMIR, London, UK, 34–41.Google Scholar
- Lie Lu, Hao Jiang, and HongJiang Zhang. 2001. A Robust Audio Classification and Segmentation Method. In Proc. of the 9th ACM Int. Conf. on Multimedia(MULTIMEDIA ’01). Association for Computing Machinery, Ottawa, CA, 203–211.Google ScholarDigital Library
- Elias Pampalk, Andreas Rauber, and Dieter Merkl. 2002. Content-based Organization and Visualization of Music Archives. In Proc. 10th ACM International Conference on Multimedia. ACM, NY, USA, 570–579.Google ScholarDigital Library
- Zafar Rafii. 2020. REPeating Pattern Extraction Technique. https://github.com/zafarrafii/REPET-Python.Google Scholar
- Andreas Rauber, Elias Pampalk, and Dieter Merkl. 2003. The SOM-enhanced JukeBox: Organization and Visualization of Music Collections Based on Perceptual Models. Journal of New Music Research 32 (06 2003), 193–210.Google Scholar
Index Terms
- Understanding Cross-Genre Rhythmic Audio Compatibility: A Computational Approach
Recommendations
Musical rhythmic pattern extraction using relevance of communities in networks
The rhythmic background of a musical piece is usually composed of featured elements that define the musical genre. For each song, such elements form rhythmic patterns, the most repetitive ones defines the rhythm of a specific musical genre and the less ...
Rhythmic Pattern Extraction by Community Detection in Complex Networks
BRACIS '14: Proceedings of the 2014 Brazilian Conference on Intelligent SystemsIn this paper, we study musical knowledge extraction and discrimination. Specifically, we propose a method for automatic extraction of drums rhythmic patterns of music and the rhythmic summarization of a set of songs from the same artist. A musical ...
Computational geometric aspects of rhythm, melody, and voice-leading
Many problems concerning the theory and technology of rhythm, melody, and voice-leading are fundamentally geometric in nature. It is therefore not surprising that the field of computational geometry can contribute greatly to these problems. The ...
Comments