Skip to content
Painless Wiener filters for audio separation
Python Shell
Branch: master
Clone or download
Type Name Latest commit message Commit time
Failed to load latest commit information.
docs try reorder Jul 5, 2019
examples fix oracle separation Mar 11, 2019
norbert Merge branch 'master' of Jan 2, 2020
tests fix tests and add test for different dtypes Jul 4, 2019
.gitignore remove transforms and images from norbert Mar 7, 2019
.travis.yml update travis Jul 5, 2019 add contributing Sep 2, 2019
LICENSE Update LICENSE May 3, 2019 add contributing Sep 2, 2019
setup.cfg remove coverage support Mar 9, 2019 update version Sep 4, 2019


Build Status Latest Version Supported Python versions DOI

Norbert is an implementation of multichannel Wiener filter, that is a very popular way of filtering multichannel audio for several applications, notably speech enhancement and source separation.

This filtering method assumes you have some way of estimating power or magnitude spectrograms for all the audio sources (non-negative) composing a mixture. If you only have a model for some target sources, and not for the rest, you may use norbert.residual_model to let Norbert create a residual model for you.

Given all source spectrograms and the mixture Time-Frequency representation, this repository can build and apply the filter that is appropriate for separation, by optimally exploiting multichannel information (like in stereo signals). This is done in an iterative procedure called Expectation Maximization, where filtering and re-estimation of the parameters are iterated.

From a beginner's perspective, all you need to do is often to call norbert.wiener with the mix and your spectrogram estimates. This should handle the rest.

From a more expert perspective, you will find the different ingredients from the EM algorithm as functions in the module as described in the API documentation


pip install norbert


Asssuming a complex spectrogram X, and a (magnitude) estimate of a target to be extracted from the spectrogram, performing the multichannel wiener filter is as simple as this:

X = stft(audio)
V = model(X)
Y = norbert.wiener(V, X)
estimate = istft(Y)

How to contribute

norbert is a community focused project, we therefore encourage the community to submit bug-fixes and requests for technical support through github issues. For more details of how to contribute, please follow our


Antoine Liutkus, Fabian-Robert Stöter


If you want to cite the Norbert software package, please use the DOI from Zenodo:




You can’t perform that action at this time.