Polytopes for music segmentation

Polytopic paradigms to study music, defined in [1], based on [2] and [3].

The goal of the polytopic approach is to define a new compression criteria, then used as cost for music segmentation, based on dynamic programming. See [4] for more details on this approach.

It can be installed with pip using pip install MusicOnPolytopes.

How to cite

You should cite the package MusicOnPolytopes, available on HAL (https://hal.archives-ouvertes.fr/hal-03151484).

Here are two styles of citations:

As a bibtex format, this should be cited as: @softwareversion{marmoret2021musiconpolytopes, title={MusicOnPolytopes}, author={Marmoret, Axel and Cohen, J{'e}r{'e}my and Bimbot, Fr{'e}d{'e}ric}, URL={https://gitlab.inria.fr/amarmore/musiconpolytopes}, LICENSE = {BSD 3-Clause ‘‘New’’ or ‘‘Revised’’ License}, year={2021}}

In the IEEE style, this should be cited as: A. Marmoret, J.E. Cohen, and F. Bimbot, “MusicOnPolytopes,” 2021, url: https://gitlab.inria.fr/amarmore/musiconpolytopes.

Credits

Code was created by Axel Marmoret (axel.marmoret@gmail.com).

The technique in itself was strongly developed by Corentin Guichaoua, Corentin Louboutin, and Frédéric Bimbot (bimbot@irisa.fr).

References

[1] A. Marmoret, J.E. Cohen, and F. Bibmot, “Polytopic Analysis of Music”, 2022, arXiv preprint arXiv:2212.11054.

[2] C. Guichaoua, “Modèles de compression et critères de complexité pour la description et l’inférence de structure musicale”, PhD thesis, Rennes 1, 2017.

[3] C. Louboutin, “Modélisation multi-échelle et multi-dimensionnelle de la structure musicale par graphes polytopiques”, PhD thesis, Rennes 1, 2019.

[4] G. Sargent, F. Bimbot, and E. Vincent, “Estimating the structural segmentation of popular music pieces under regularity constraints”, IEEE/ACM Transactions on Audio, Speech, and Language Processing, 25(2), 2016, pp. 344-358.