Dataset Open Access

Open-Unmix for Speech Enhancement (UMX SE)

Uhlich, Stefan; Mitsufuji, Yuki

Weights of Open-Unmix trained on the 28-speaker version of Voicebank+Demand (Sampling rate: 16kHz). The weights can be used with open-unmix-nnabla and open-unmix-pytorch.

Files (25.5 MB)
Name Size
noise.onnx
md5:db366f981b167259b41464f789ae8ebf 		6.3 MB Download
noise_04a6fc2d.pth
md5:f2a0ae404d9717a5c90b08f6454bd214 		6.4 MB Download
speech.onnx
md5:f557c5d7465457ba185d1940e040907b 		6.3 MB Download
speech_f5e0d9f9.pth
md5:bf529a6c42766591cab86319880814d6 		6.4 MB Download
training_json.zip
md5:f3c6e2f58a94760c536194563f20be1a 		55.2 kB Download
675
11,260
views
downloads
All versions This version
Views 675675
Downloads 11,26011,260
Data volume 71.2 GB71.2 GB
Unique views 578578
Unique downloads 1,4361,436
More info on how stats are collected.
Indexed in
Publication date:
May 5, 2020
DOI:
10.5281/zenodo.3786908

Zenodo DOI Badge

DOI 

10.5281/zenodo.3786908

Markdown 

[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3786908.svg)](https://doi.org/10.5281/zenodo.3786908)

reStructedText 

.. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.3786908.svg
   :target: https://doi.org/10.5281/zenodo.3786908

HTML 

<a href="https://doi.org/10.5281/zenodo.3786908"><img src="https://zenodo.org/badge/DOI/10.5281/zenodo.3786908.svg" alt="DOI"></a>

Image URL 

https://zenodo.org/badge/DOI/10.5281/zenodo.3786908.svg

Target URL 

https://doi.org/10.5281/zenodo.3786908

Keyword(s):
Source Separation Speech Enhancement NNabla PyTorch
Communities:
License (for files):
MIT License

Versions

Version 1 10.5281/zenodo.3786908 May 5, 2020
Cite all versions? You can cite all versions by using the DOI 10.5281/zenodo.3786907. This DOI represents all versions, and will always resolve to the latest one. Read more.

Share

Cite as

Export