Music Source Separation

53 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 )

Libraries

Use these libraries to find Music Source Separation models and implementations

Latest papers with no code

Why does music source separation benefit from cacophony?

no code yet • 28 Feb 2024

In music source separation, a standard training data augmentation procedure is to create new training samples by randomly combining instrument stems from different songs.

Real-time Low-latency Music Source Separation using Hybrid Spectrogram-TasNet

no code yet • 27 Feb 2024

There have been significant advances in deep learning for music demixing in recent years.

SCNet: Sparse Compression Network for Music Source Separation

no code yet • 24 Jan 2024

We use a higher compression ratio on subbands with less information to improve the information density and focus on modeling subbands with more information.

Resource-constrained stereo singing voice cancellation

no code yet • 22 Jan 2024

We study the problem of stereo singing voice cancellation, a subtask of music source separation, whose goal is to estimate an instrumental background from a stereo mix.

Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inference

no code yet • 6 Dec 2023

Deploying neural networks to different devices or platforms is in general challenging, especially when the model size is large or model complexity is high.

Pre-trained Spatial Priors on Multichannel NMF for Music Source Separation

no code yet • 9 Oct 2023

This paper presents a novel approach to sound source separation that leverages spatial information obtained during the recording setup.

MBTFNet: Multi-Band Temporal-Frequency Neural Network For Singing Voice Enhancement

no code yet • 6 Oct 2023

A typical neural speech enhancement (SE) approach mainly handles speech and noise mixtures, which is not optimal for singing voice enhancement scenarios.

Self-refining of Pseudo Labels for Music Source Separation with Noisy Labeled Data

no code yet • 24 Jul 2023

Music source separation (MSS) faces challenges due to the limited availability of correctly-labeled individual instrument tracks.

Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT

no code yet • 4 Apr 2023

In this paper, we propose a self-supervised learning framework for music source separation inspired by the HuBERT speech representation model.

Hybrid Y-Net Architecture for Singing Voice Separation

no code yet • 5 Mar 2023

This research paper presents a novel deep learning-based neural network architecture, named Y-Net, for achieving music source separation.