Jay Taylor's notes

back to listing index

speechLabBcCuny/onssen: An open-source speech separation and enhancement library

[web search]
Original source (github.com)
Tags: signal-processing blind-source-separation audio-processing audio-source-separation github.com
Clipped on: 2020-01-28

Skip to content
Image (Asset 1/3) alt= You have unread notifications
An open-source speech separation and enhancement library
Python
Branch: master
New pull request
Clone or download
Image (Asset 3/3) alt= 1
Latest commit 0479d78 on Nov 29, 2019

README.md

ONSSEN: An Open-source Speech Separation and Enhancement Library

Supported Models

  • Deep Clustering
  • Chimera Net
  • Chimera++
  • Phase Estimation Network
  • Speech Enhancement with Restoration Layers

Supported Dataset

Requirements

  • PyTorch
  • LibRosa
  • NumPy

Usage

You can simply use the existing config JSON file or customize your config file to train the enhancement or separation model.

python train.py -c configs/dc_config.json

Citing

If you use onssen for your research project, please cite one of the following bibtex citations:

@inproceedings {onssen,
    author = {Zhaoheng Ni and Michael Mandel},
    title = "ONSSEN: An Open-source Speech Separation and Enhancement Library",
    publisher = "under review",
    year = 2019
}

@Misc{onssen,
    author = {Zhaoheng Ni and Michael Mandel},
    title = "ONSSEN: An Open-source Speech Separation and Enhancement Library",
    howpublished = {\url{https://github.com/speechLabBcCuny/onssen}},
    year =        {2019}
}