About
Audio Source Separation is the process of separating a mixture (e.g. a pop band recording) into isolated sounds from individual sources (e.g. just the lead vocals).
Source: Model selection for deep audio source separation via clustering analysis
Benchmarks
| TREND | DATASET | BEST METHOD | PAPER TITLE | PAPER | CODE | COMPARE |
|---|---|---|---|---|---|---|
|
||||||
|
Datasets
Greatest papers with code
Sudo rm -rf: Efficient Networks for Universal Audio Source Separation
In this paper, we present an efficient neural network for end-to-end general purpose audio source separation.
Ranked #8 on
Speech Separation
on wsj0-2mix
Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation
• f90/Wave-U-Net
• 
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.
Ranked #16 on
Music Source Separation
on MUSDB18
Multi-scale Multi-band DenseNets for Audio Source Separation
This paper deals with the problem of audio source separation.
Audio-Visual Scene Analysis with Self-Supervised Multisensory Features
ECCV 2018
• andrewowens/multisensory
•
The thud of a bouncing ball, the onset of speech as lips open -- when visual and audio events occur together, it suggests that there might be a common, underlying event that produced both signals.
Improved Speech Enhancement with the Wave-U-Net
• craigmacartney/Wave-U-Net-For-Speech-Enhancement
•
We study the use of the Wave-U-Net architecture for speech enhancement, a model introduced by Stoller et al for the separation of music vocals and accompaniment.
Ranked #9 on
Speech Enhancement
on DEMAND
AUDIO SOURCE SEPARATION SPEECH ENHANCEMENT SPEECH RECOGNITION
The Cone of Silence: Speech Separation by Localization
NeurIPS 2020
• vivjay30/Cone-of-Silence
• 
Given a multi-microphone recording of an unknown number of speakers talking concurrently, we simultaneously localize the sources and separate the individual speakers.
Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice Extraction
• f90/AdversarialAudioSeparation
•
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.
AUDIO SOURCE SEPARATION DATA AUGMENTATION MUSIC SOURCE SEPARATION
Co-Separating Sounds of Visual Objects
ICCV 2019
• rhgao/co-separation
•
Learning how objects sound from video is challenging, since they often heavily overlap in a single audio channel.
Ranked #1 on
Audio Source Separation
on MUSIC (multi-source)
Learning to Separate Object Sounds by Watching Unlabeled Video
ECCV 2018
• rhgao/separating-object-sounds
•
Our work is the first to learn audio source separation from large-scale "in the wild" videos containing multiple audio sources per video.
AUDIO DENOISING AUDIO SOURCE SEPARATION DENOISING MULTI-LABEL LEARNING
AutoClip: Adaptive Gradient Clipping for Source Separation Networks
• pseeth/autoclip
•
Clipping the gradient is a known approach to improving gradient descent, but requires hand selection of a clipping threshold hyperparameter.