Tutorial Demucs (Music Source Separation)

Tutorial

Demucs (Music Source Separation) - Printable Version

+- PinoStudio 1 (https://pinostudio1.com)
+-- Forum: Informatica (https://pinostudio1.com/forumdisplay.php?fid=7)
+--- Forum: Programacion, Desarrollo Web (https://pinostudio1.com/forumdisplay.php?fid=8)
+--- Thread:

Tutorial

Demucs (Music Source Separation) (/showthread.php?tid=2148)

Demucs (Music Source Separation) - DiegoPino - 03-27-2020

Demucs Music Source Separation in the Waveform Domain

We provide an implementation of Demucs and Conv-Tasnet for music source separation on the MusDB dataset. They can separate drums, bass and vocals from the rest with state-of-the-art results, surpassing previous waveform or spectrogram based methods. The architecture and results obtained are detailed in our paper Music Source Separation in the waveform domain.

Demucs is based on U-Net convolutional architecture inspired by Wave-U-Net and SING, with GLUs, a BiLSTM between the encoder and decoder, specific initialization of weights and transposed convolutions in the decoder.

Conv-Tasnet is a separation model developed for speech which predicts a mask on a learnt over-complete linear representation using a purely convolutional model with stride of 1 and dilated convolutional blocks. We reused the code from the kaituoxu/Conv-TasNet repository and added support for multiple audio channels.

When trained only on MusDB, Conv-Tasnet achieves higher SDR than Demucs (5.7 vs 5.6). However, the audio it generates has significant artifacts as measured by human evaluations (MOS is 3.2 for Demucs, 2.9 for Conv-Tasnet). When trained with extra training data, Demucs and Conv-Tasnet obtain the same SDR. See our paper Section 6 for more details or listen to our audio samples .

[Image: demucs.png]

Using Mac OS X

If you do not already have Anaconda installed or much experience with the terminal on Mac OS X here are some detailed instructions:

1. Download Anaconda 3.7 64 bits for MacOS: https://www.anaconda.com/distribution/#download-section
2. Open Anaconda Prompt in MacOSX: https://docs.anaconda.com/anaconda/user-guide/getting-started/#open-nav-mac
3. Follow these commands:

Code:
cd ~

conda install git

git clone https://github.com/facebookresearch/demucs

cd demucs

conda env update -f environment-cpu.yml

conda activate demucs

python3 -m demucs.separate --dl -n demucs -d cpu PATH_TO_AUDIO_FILE_1

You can drag the .mp3 file to the console and it will paste the mp3 path. To later reuse Demucs, simply start again the Anaconda Prompt and run

Code:
cd ~/demucs

python3 -m demucs.separate --dl -n demucs -d cpu PATH_TO_AUDIO_FILE_1

Nota Importante:
En mi computador que tiene problemas de memoria y capacidad, debo usar el siguiente código, con este código me funciona para separar los Tracks en MULTIPISTA.

Code:
python3 -m demucs.separate --dl -n tasnet /Path_to_music/any_song.mp3 -d cpu

Referencia:
- https://github.com/facebookresearch/demucs
- https://github.com/facebookresearch/demucs/issues/36

Big Grin