ssspy

A Python toolkit for sound source separation.

Build Status

| Python | Ubuntu | MacOS (x86_64) | MacOS (arm64) | Windows | |:-:|:-:|:-:|:-:|:-:| | 3.9 | | | | | | 3.10 | | | | | | 3.11 | | | | | | 3.12 | | | | |

Installation

You can install by pip.

pip install ssspy

To install latest version,

pip install git+https://github.com/tky823/ssspy.git

Instead, you can build package from source.

git clone https://github.com/tky823/ssspy.git
cd ssspy
pip install .

If you cannot install ssspy due to failure in building wheel for numpy, please install numpy in advance.

Build Documentation Locally (optional)

To build the documentation locally, you have to include docs and notebooks when installing ssspy.

pip install -e ".[docs,notebooks]"

You need to convert some notebooks by the following command:

# in ssspy/
. ./docs/pre_build.sh

When you build the documentation, run the following command.

cd docs/
make html

Or, you can build the documentation automatically using sphinx-autobuild.

# in ssspy/
sphinx-autobuild docs docs/_build/html

Blind Source Separation Methods

| Method | Notebooks | |:-:|:-:| | Independent Component Analysis (ICA) [1-3] | Gradient-descent-based ICA: <br> Natural-gradient-descent-based ICA: <br> Fast ICA: | | Frequency-Domain Independent Component Analysis (FDICA) [4-6] | Gradient-descent-based FDICA: <br> Natural-gradient-descent-based FDICA: <br> Auxiliary-function-based FDICA (IP1): <br> Auxiliary-function-based FDICA (IP2): <br> Gradient-descent-based Laplace-FDICA: <br> Natural-gradient-descent-based Laplace-FDICA: <br> Auxiliary-function-based Laplace-FDICA (IP1): <br> Auxiliary-function-based Laplace-FDICA (IP2): | | Independent Vector Analysis (IVA) [7-14] | Gradient-descent-based IVA: <br> Natural-gradient-descent-based IVA: <br> Fast IVA: <br> Faster IVA: <br> Auxiliary-function-based IVA (IP1): <br> Auxiliary-function-based IVA (IP2): <br> Auxiliary-function-based IVA (ISS1): <br> Auxiliary-function-based IVA (ISS2): <br> Auxiliary-function-based IVA (IPA): <br> Gradient-descent-based Laplace-IVA: [![Open in Colab](https://colab.research.google.com/assets/c