https://github.com/fgnt/pb_bss

Collection of EM algorithms for blind source separation of audio signals

https://github.com/fgnt/pb_bss

Science Score: 34.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
    Organization fgnt has institutional domain (nt.uni-paderborn.de)
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.9%) to scientific vocabulary

Keywords

beamforming bss em-algorithm multi-channel source-separation speech-enhancement speech-processing
Last synced: 4 months ago · JSON representation

Repository

Collection of EM algorithms for blind source separation of audio signals

Basic Info
  • Host: GitHub
  • Owner: fgnt
  • License: mit
  • Language: Python
  • Default Branch: master
  • Homepage:
  • Size: 638 KB
Statistics
  • Stars: 294
  • Watchers: 12
  • Forks: 62
  • Open Issues: 4
  • Releases: 0
Topics
beamforming bss em-algorithm multi-channel source-separation speech-enhancement speech-processing
Created over 8 years ago · Last pushed 9 months ago
Metadata Files
Readme License

README.md

Blind Source Separation (BSS) algorithms

pytest Build Status Azure DevOps tests Azure DevOps coverage MIT License

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

Owner

  • Name: Department of Communications Engineering University of Paderborn
  • Login: fgnt
  • Kind: organization
  • Location: Paderborn, Germany

GitHub Events

Total
  • Watch event: 21
  • Issue comment event: 2
  • Push event: 4
  • Pull request event: 2
  • Fork event: 4
  • Create event: 1
Last Year
  • Watch event: 21
  • Issue comment event: 2
  • Push event: 4
  • Pull request event: 2
  • Fork event: 4
  • Create event: 1

Dependencies

setup.py pypi
  • Metric *
  • cached_property *
  • dataclasses *
  • einops *
  • matplotlib *
  • mir_eval *
  • pesq *
  • pystoi *
  • scikit-learn *
  • srmrpy *
  • sympy *
.github/workflows/tests.yml actions
  • actions/checkout v2 composite
  • actions/setup-python v2 composite