Info: Zenodo’s user support line is staffed on regular business days between Dec 23 and Jan 5. Response times may be slightly longer than normal.

SigSep: Open Resources for Audio Source Separation
Published May 5, 2020 | Version v1
Dataset Open

Open-Unmix for Speech Enhancement (UMX SE)

Creators

  • 1. Sony Europe B.V.
  • 2. Sony Corporation

Description

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

training_json.zip

Files (25.5 MB)

Name Size Download all
md5:db366f981b167259b41464f789ae8ebf
6.3 MB Download
md5:f2a0ae404d9717a5c90b08f6454bd214
6.4 MB Download
md5:f557c5d7465457ba185d1940e040907b
6.3 MB Download
md5:bf529a6c42766591cab86319880814d6
6.4 MB Download
md5:f3c6e2f58a94760c536194563f20be1a
55.2 kB Preview Download