Music Source Separation

55 papers with code • 3 benchmarks • 7 datasets

Music source separation is the task of decomposing music into its constitutive components, e. g., yielding separated stems for the vocals, bass, and drums.

( Image credit: SigSep )


Use these libraries to find Music Source Separation models and implementations

Most implemented papers

Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation

naplab/Conv-TasNet 20 Sep 2018

The majority of the previous methods have formulated the separation problem through the time-frequency representation of the mixed signal, which has several drawbacks, including the decoupling of the phase and magnitude of the signal, the suboptimality of time-frequency representation for speech separation, and the long latency in calculating the spectrograms.

Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation

f90/Wave-U-Net 8 Jun 2018

Models for audio source separation usually operate on the magnitude spectrum, which ignores phase information and makes separation performance dependant on hyper-parameters for the spectral front-end.

Multi-scale Multi-band DenseNets for Audio Source Separation

Anjok07/ultimatevocalremovergui 29 Jun 2017

This paper deals with the problem of audio source separation.

All for One and One for All: Improving Music Separation by Bridging Networks

asteroid-team/asteroid 8 Oct 2020

This paper proposes several improvements for music separation with deep neural networks (DNNs), namely a multi-domain loss (MDL) and two combination schemes.

Music Source Separation with Band-split RNN

amanteur/BandSplitRNN-Pytorch 30 Sep 2022

The performance of music source separation (MSS) models has been greatly improved in recent years thanks to the development of novel neural network architectures and training pipelines.

Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction

f90/AdversarialAudioSeparation 31 Oct 2017

Based on this idea, we drive the separator towards outputs deemed as realistic by discriminator networks that are trained to tell apart real from separator samples.

Spleeter: A Fast And State-of-the Art Music Source Separation Tool With Pre-trained Models

deezer/spleeter ISMIR 2019 Late-Breaking/Demo 2019

We present and release a new tool for music source separation with pre-trained models called Spleeter. Spleeter was designed with ease of use, separation performance and speed in mind.

Primal-Dual Algorithms for Non-negative Matrix Factorization with the Kullback-Leibler Divergence

felipeyanez/nmf 4 Dec 2014

Non-negative matrix factorization (NMF) approximates a given matrix as a product of two non-negative matrices.

End-to-end music source separation: is it possible in the waveform domain?

francesclluis/source-separation-wavenet 29 Oct 2018

Most of the currently successful source separation techniques use the magnitude spectrogram as input, and are therefore by default omitting part of the signal: the phase.

Multi-channel U-Net for Music Source Separation

kvsphantom/multitask-unet-bss 23 Mar 2020

However, Conditioned U-Net (C-U-Net) uses a control mechanism to train a single model for multi-source separation and attempts to achieve a performance comparable to that of the dedicated models.