Open-Unmix for Speech Enhancement (UMX SE)
Lists
Only you see this
Abstract
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.
BibTeX
@inproceedings{uhlich2020open,
author = {Stefan Uhlich and Yuki Mitsufuji},
title = {{Open-Unmix for Speech Enhancement (UMX SE)}},
booktitle = {Zenodo},
year = {2020},
doi = {10.5281/zenodo.3786907},
}Loading related content...