Skip to main content

EM algorithms for integrated spatial and spectral models.

Project description

Blind Source Separation (BSS) algorithms

Build Status Azure DevOps tests Azure DevOps coverage MIT License

Fork note : The original repo has been modified to allow a partial release of the evaluation utilities on PyPI under the name pb_bss_eval. All the credits goes to the original authors (see here).
As can be seen in the Manifest.in, only the evaluation sub-package can be installed and is released on PyPI. To install it, just run :

pip install numpy Cython  # required for pesq install
pip install pb_bss_eval

This repository covers EM algorithms to separate speech sources in multi-channel recordings.

In particular, the repository contains methods to integrate Deep Clustering (a neural network-based source separation algorithm) with a probabilistic spatial mixture model as proposed in the Interspeech paper "Tight integration of spatial and spectral features for BSS with Deep Clustering embeddings" presented at Interspeech 2017 in Stockholm.

@InProceedings{Drude2017DeepClusteringIntegration,
  Title                    = {Tight integration of spatial and spectral features for {BSS} with Deep Clustering embeddings},
  Author                   = {Drude, Lukas and and Haeb-Umbach, Reinhold},
  Booktitle                = {INTERSPEECH 2017, Stockholm, Sweden},
  Year                     = {2017},
  Month                    = {Aug}
}

Installation

Install it directly from source

git clone https://github.com/fgnt/pb_bss.git
cd pb_bss
pip install --editable .

We expect that numpy, scipy and cython are installed (e.g. conda install numpy scipy cython or pip install numpy scipy cython).

The default option is to install only the necessary dependencies. When you want to run the tests or execute the notebooks, use the one of the following commands for the installation:

pip install --editable .[all]  # Without a whitespace between `.` and `[all]`
pip install git+https://github.com/fgnt/pb_bss.git#egg=pb_bss[all]

Project details


Release history Release notifications

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for pb-bss-eval, version 0.0.1
Filename, size File type Python version Upload date Hashes
Filename, size pb_bss_eval-0.0.1-py3-none-any.whl (14.5 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size pb_bss_eval-0.0.1.tar.gz (12.6 kB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page