research data . Dataset . 2020

Open-Unmix for Speech Enhancement (UMX SE)

Uhlich, Stefan; Mitsufuji, Yuki;
Open Source
  • Published: 05 May 2020
  • Publisher: Zenodo
Abstract
<p>Weights of Open-Unmix trained on the 28-speaker version of Voicebank+Demand (Sampling rate: 16kHz). The weights can be used with <a href="https://github.com/sigsep/open-unmix-nnabla">open-unmix-nnabla</a> and <a href="https://github.com/sigsep/open-unmix-pytorch">open-unmix-pytorch</a>.</p>
Subjects
free text keywords: Source Separation, Speech Enhancement, NNabla, PyTorch, Biochemistry, Microbiology, Molecular Biology, Neuroscience, 111714 Mental Health, Space Science
Download fromView all 4 versions
Zenodo
Dataset . 2020
Provider: Datacite
Zenodo
Dataset . 2020
Provider: Datacite
figshare
Dataset . 2020
Provider: figshare
Any information missing or wrong?Report an Issue