Metadata-Version: 2.1
Name: as-seg
Version: 0.1.0
Summary: Package for the segmentation of autosimilarity matrices.
Home-page: https://gitlab.inria.fr/amarmore/autosimilarity_segmentation
Author: Marmoret Axel
Author-email: axel.marmoret@irisa.fr
License: BSD
Classifier: License :: OSI Approved :: BSD License
Classifier: Programming Language :: Python
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Multimedia :: Sound/Audio :: Analysis
Classifier: Programming Language :: Python :: 3.8
Requires-Python: >=3.7.*
Description-Content-Type: text/markdown
License-File: LICENSE.md
License-File: AUTHORS
Requires-Dist: librosa (>=0.8.0)
Requires-Dist: madmom (>=0.16.1)
Requires-Dist: matplotlib
Requires-Dist: mir-eval (>=0.6)
Requires-Dist: mirdata (>=0.3.3)
Requires-Dist: numpy (>=1.18.2)
Requires-Dist: pandas
Requires-Dist: scipy (>=1.4.1)
Requires-Dist: sklearn
Requires-Dist: soundfile
Requires-Dist: tensorly (>=0.5.1)

# as_seg: module for computing and segmenting autosimilarity matrices. #

Hello, and welcome on this repository!

This project aims at computing autosimilarity matrices, and segmenting them, which consists of the task of structural segmentation.

The current version contains the CBM algorithm [1], along with a (low-effort) implementation of Foote's novelty algorithm [2].

This is a first release, and may contain bug. Comments are welcomed!

## Tutorial notebook ##

A tutorial notebook presenting the most important components of this toolbox is available in the folder "Notebooks" (called "Walkthrough").

## Software version ##

This code was developed with Python 3.8.5, and some external libraries detailed in dependencies.txt. They should be installed automatically if this project is downloaded using pip.

## Credits ##

Code was created by Axel Marmoret (<axel.marmoret@irisa.fr>), and strongly supported by Jeremy E. Cohen (<jeremy.cohen@cnrs.fr>).

The technique in itself was also developed by FrÃ©dÃ©ric Bimbot (<bimbot@irisa.fr>).

## References ##
[1] Marmoret, A., Cohen, J. E., & Bimbot, F., "Convolutive Block-Matching Segmentation Algorithm with Application to Music Structure Analysis", 2022, arXiv preprint arXiv:2210.15356.

[2] Foote, J., "Automatic audio segmentation using a measure of audio novelty", in: 2000 IEEE Int. Conf. Multimedia and Expo. ICME2000. Proc. Latest Advances in the Fast Changing World of Multimedia, vol. 1, IEEE, 2000,pp. 452â€“455.
