A two-stage U-Net for high-fidelity denoising of historical recordings
Official repository of the paper (not submitted yet):
E. Moliner and V. Välimäki,, "A two-stage U-Net for high-fidelity denosing of historical recordinds", in Proc. IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Singapore, May, 2022
Abstract
Enhancing the sound quality of historical music recordings is a long-standing problem. This paper presents a novel denoising method based on a fully-convolutional deep neural network. A two-stage U-Net model architecture is designed to model and suppress the degradations with high fidelity. The method processes the time-frequency representation of audio, and is trained using realistic noisy data to jointly remove hiss, clicks, thumps, and other common additive disturbances from old analog discs. The proposed model outperforms previous methods in both objective and subjective metrics. The results of a formal blind listening test show that the method can denoise real gramophone recordings with an excellent quality. This study shows the importance of realistic training data and the power of deep learning in audio restoration.
Listen to our audio samples
Requirements
You will need at least python 3.7 and CUDA 10.1 if you want to use GPU. See requirements.txt for the required package versions.
To install the environment through anaconda, follow the instructions:
conda env update -f environment.yml
conda activate historical_denoiser
Denoising Recordings
Run the following commands to clone the repository and install the pretrained weights of the two-stage U-Net model:
git clone https://github.com/eloimoliner/denoising-historical-recordings.git
cd denoising-historical-recordings
wget https://github.com/eloimoliner/denoising-historical-recordings/releases/download/v0.0/checkpoint.zip
unzip checkpoint.zip /experiments/trained_model/
If the environment is installed correctly, you can denoise an audio file by running:
bash inference.sh "file name"
A ".wav" file with the denoised version, as well as the residual noise and the original signal in "mono", will be generated in the same directory as the input file.
Training
TODO
51 Nov 09, 2022
55 Sep 14, 2022
3 Aug 29, 2022
20 Jun 21, 2022
1 Dec 19, 2021
99 Dec 27, 2022
45 Nov 29, 2022
116 Dec 12, 2022
6 Nov 07, 2022
48 Dec 23, 2022
17 Dec 06, 2022
6 Aug 09, 2022
7 Sep 15, 2022
2 Oct 20, 2022
12 Nov 24, 2022
[email protected]">
84 Dec 12, 2022
36 Oct 18, 2022
37 Oct 23, 2022
3 Jan 11, 2022
115 Dec 17, 2022