Implementation of the [Wave-U-Net] for audio source separation.

The Wave-U-Net is a convolutional neural network applicable to audio source separation tasks, which works directly on the raw audio waveform, presented in [this paper].

The Wave-U-Net is an adaptation of the U-Net architecture to the one-dimensional time domain to perform end-to-end audio source separation. Through a series of downsampling and upsampling blocks, which involve 1D convolutions combined with a down-/upsampling process, features are computed on multiple scales/levels of abstraction and time resolution, and combined to make a prediction.

See the diagram below for a summary of the network architecture.

The Wave-U-Net also participated in the SiSec separation campaign as submissions STL1 and STL2 and achieved a good performance, especially considering the limited dataset we used compared to many other submissions despite having a more data-hungry end-to-end approach (we have to learn the frequency decomposition front-end from data as well).

GPU strongly recommended to avoid very long training times. Python 2.7 Python package requirements below:

sacred==0.7.3
tensorflow-gpu==1.8.0
librosa==0.6.1
scikit-image==0.13.1
soundfile==0.10.2
scikits.audiolab==0.11.0
lxml==4.2.1
musdb==0.2.3
museval==0.2.0

These required packages are also saved in the file requirements.txt located in this repository, so you can clone the repository and then execute the following in the downloaded repository's path to install all the required packages at once:

pip install -r requirements.txt

To reproduce the experiments in the paper, you need to download the datasets below. You can of course use your own datasets for separation, but for this you would need to modify the code manually, which will not be discussed here.

Download the full MUSDB18 dataset from https://sigsep.github.io/datasets/musdb.html and extract it into a folder of your choice. It should have two subfolders: "test" and "train" as well as a README.md file.

If you want to replicate the vocal separation experiments and not only the multi-instrument experiments, you also need to download the CCMixter vocal separation database from https://members.loria.fr/ALiutkus/kam/. Extract this dataset into a folder of your choice. Its main folder should contain one subfolder for each song.

Now you need to set up the correct file paths for the datasets and the location where source estimates should be saved.

Open the Training.py file, and set the musdb_path entry of the model_config dictionary to the location of the main folder of the MUSDB18 dataset. Also set the estimates_path entry of the same model_config dictionary to the path pointing to an empty folder where you want the final source estimates of the model to be saved into.

If you use CCMixter, open the CCMixter.xml in the main repository folder, and replace the given file path tagged as databaseFolderPath with your path to the main folder of CCMixter.

Since the paper investigates many model variants of the Wave-U-Net and also trains the [U-Net proposed for vocal separation], which achieved state-of-the-art performance, as a comparison, we give a list of model variants to train and the command needed to start training them: