scikit-maad is a free, open-source and modular toolbox to analyze ecoacoustics datasets in Python 3. This package was designed to bring flexibility to (1) find regions of interest, and (2) to compute acoustic features in audio recordings. This workflow opens the possibility to use powerfull machine learning algorithms through scikit-learn, allowing to identify key patterns in all kind of soundscapes.

• See Howto notebook in "docs" directory for detail explanations
• See Python scripts in "examples" directory for a direct approach of MAAD
• In depth information related to the Multiresolution Analysis of Acoustic Diversity implemented in scikit-maad was published in: Ulloa, J. S., Aubin, T., Llusia, D., Bouveyron, C., & Sueur, J. (2018). Estimating animal acoustic diversity in tropical environments using unsupervised multiresolution analysis. Ecological Indicators, 90, 346–355

scikit-maad dependencies:

• Python >= 3.5
• NumPy >= 1.13
• SciPy >= 0.18
• scikit-image >= 0.14

scikit-maad is hosted on PyPI. To install, run the following command in your Python environment:

$ pip install scikit-maad

To install the latest version from source clone the master repository and from the top-level folder call:

$ python setup.py install

This work started in 2016 at the Museum National d'Histoire Naturelle (MNHN) in Paris, France. It was initiated by Juan Sebastian Ulloa, supervised by Jérôme Sueur and Thierry Aubin at the Muséum National d'Histoire Naturelle and the Université Paris Saclay respectively. Python functions were added by Sylvain Haupert and Chloe Huetz in 2018. New features are currently being developped and a stable release will be available by the end of 2019.