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
347
173
views
downloads
All versions This version
Views 347347
Downloads 173173
Data volume 947.8 MB947.8 MB
Unique views 288288
Unique downloads 7070

Share

Cite as