Samples for Audio Denoising with Deep Network Priors

A comparison of our unsupervised audio denoising based on deep network priors method with the classical unsupervised audio denoising baselines.

It seems that our results are cleaner and put less distortion to the speech signal. We outperform the baselines in any evaluation metric, given in our paper

Audio Demo on Evaluation subset: (better to use headphones)

Name Noisy Sample Clean Sample Our - DNP Connected-Frequency Doblinger Hirsch IMCRA Martin MCRA MCRA2
p232_001
p232_002
p232_003
p232_005
p232_006
p257_001
p257_002
p257_003
p257_004
p232_017
p232_019
p232_020
p232_021
p257_136
p257_137
p257_138
p257_139