Abstract
Repetition-based modelling of melody segmentation relies on identifying and selecting repetitions of melodic fragments. At present, automatic repetition identification results in an overwhelmingly large number of repetitions, requiring the application of constraints for selecting relevant repetitions. This paper proposes constraints based on the locations of repetitions, extending existing approaches on constraints based on repetition length and frequency, and the temporal overlap between repetitions. To test our constraints, we incorporate them in a state-of-the-art repetition-based segmentation model. The original and constraint-extended versions of the model are used to segment 400 (symbolically encoded) folk melodies. Results show the constraint-extended version of the model achieves a statistically significant 14 % average improvement over the model’s original version.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Since \(\sigma \in \mathbb {R}_{\ge 0}\), normalisation of the \(\lambda _1\) values is required.
- 2.
While theoretically \(\lambda _2 \in [0,1]\), considering \(\lim _{\mathcal {O}\rightarrow N} \lambda _2(\mathcal {O})=1\), in practice the values of \(\lambda _2\) will never reach the maximum of the function’s range, and so re-scaling is required.
- 3.
- 4.
- 5.
Vocal music has dominated previous evaluations of melodic segmentation (especially large-scale evaluations), which might give an incomplete picture of the overall performance and generalisation computational segmentation models.
- 6.
The samples are taken randomly from the EFSC and LC. However, following the corpus cleaning procedures of [18], we filtered out melodies which contained rests at annotated phrase markings, and also excluded melodies with just one phrase. The reason to exclude melodies with rests at annotated phrase markings is that, according to transcription research, sometimes musicologists transcribing the folk melodies would use rests at phrases as ‘breath marks’, regardless of whether performers would actually take breaths or not, making these rests an artefact of the transcription process (for a more detailed discussion on this topic see [18]).
- 7.
Instructions to annotate boundaries were related to performance practice (e.g. “where would you change the movement of the bow”). The annotators agreed on a single segmentation, so no inter-annotator-agreement analysis is possible.
- 8.
We tested both standard thresholding and the thresholding method provided in the SM toolbox (with the default parameters). We also tested Gaussian smoothing with window sizes \(\in \{2,3,6\}\) notes.
References
Ahlbäck, S.: Melodic similarity as a determinant of melody structure. Musicae Sci. 11(1), 235–280 (2007)
Cambouropoulos, E.: The local boundary detection model (LBDM) and its application in the study of expressive timing. In: Proceedings of the International Computer Music Conference (ICMC 2001), pp. 232–235 (2001)
Cambouropoulos, E.: Musical parallelism and melodic segmentation. Music Percept. 23(3), 249–268 (2006)
Huron, D.: Sweet Anticipation: Music and the Psychology of Expectation. MIT press, Cambridge (2006)
Lartillot, O.: Reflections towards a generative theory of musical parallelism. Musicae Sci. Discuss. Forum 5, 195–229 (2010)
Lerdahl, F., Jackendoff, R.: A Generative Theory of Tonal Music. MIT press, Cambridge (1983)
Margulis, E.H.: Musical repetition detection across multiple exposures. Music Percept. Interdisc. J. 29(4), 377–385 (2012)
Meredith, D., Lemström, K., Wiggins, G.A.: Algorithms for discovering repeated patterns in multidimensional representations of polyphonic music. J. New Music Res. 31(4), 321–345 (2002)
Müller, M., Grosche, P., Jiang, N.: A segment-based fitness measure for capturing repetitive structures of music recordings. In: ISMIR, pp. 615–620 (2011)
Müller, M., Jiang, N., Grohganz, H.: SM toolbox: matlab implementations for computing and enhancing similarity matrices. In: Audio Engineering Society Conference: 53rd International Conference: Semantic Audio. Audio Engineering Society (2014)
Müller, M., Jiang, N., Grosche, P.: A robust fitness measure for capturing repetitions in music recordings with applications to audio thumbnailing. IEEE Trans. Audio Speech Lang. Process. 21(3), 531–543 (2013)
Müller, M., Grosche, P.: Automated segmentation of folk song field recordings. In: Proceedings of the ITG Conference on Speech Communication, Braunschweig, Germany (2012)
Müller, M., Kurth, F.: Enhancing similarity matrices for music audio analysis. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 5 (2006)
Pearce, M., Müllensiefen, D., Wiggins, G.: The role of expectation and probabilistic learning in auditory boundary perception: a model comparison. Perception 39(10), 1365 (2010)
Rodríguez-López, M., Volk, A.: Symbolic segmentation: a corpus-based analysis of melodic phrases. In: Aramaki, M., Derrien, O., Kronland-Martinet, R., Ystad, S. (eds.) CMMR 2013. LNCS, vol. 8905, pp. 548–557. Springer, Heidelberg (2014)
Rodríguez-López, M., Bountouridis, D., Volk, A.: Multi-strategy segmentation of melodies. In: Proceedings of the 15th Conference of the International Society for Music Information Retrieval (ISMIR), pp. 207–212 (2014)
Rodríguez-López, M., Volk, A., de Haas, W.: Comparing repetition-based melody segmentation models. In: Proceedings of the 9th Conference on Interdisciplinary Musicology (CIM), pp. 143–148 (2014)
Shanahan, D., Huron, D.: Interval size and phrase position: a comparison between german and chinese folksongs (2011)
Takasu, A., Yanase, T., Kanazawa, T., Adachi, J.: Music structure analysis and its application to theme phrase extraction. In: Abiteboul, S., Vercoustre, A.-M. (eds.) ECDL 1999. LNCS, vol. 1696, pp. 92–105. Springer, Heidelberg (1999)
Temperley, D.: The Cognition of Basic Musical Structures. MIT press, Cambridge (2004)
Acknowledgements
We thank the anonymous reviewers for the useful comments on earlier drafts of this document. Marcelo Rodríguez López and Anja Volk are supported by the Netherlands Organization for Scientific Research (NWO-VIDI grant 276-35-001).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Rodríguez-López, M.E., Volk, A. (2015). Location Constraints for Repetition-Based Segmentation of Melodies. In: Collins, T., Meredith, D., Volk, A. (eds) Mathematics and Computation in Music. MCM 2015. Lecture Notes in Computer Science(), vol 9110. Springer, Cham. https://doi.org/10.1007/978-3-319-20603-5_7
Download citation
DOI: https://doi.org/10.1007/978-3-319-20603-5_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-20602-8
Online ISBN: 978-3-319-20603-5
eBook Packages: Computer ScienceComputer Science (R0)