SOTAVerified

Audio Source Separation

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

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–30 of 112 papers

TitleStatusHype
Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation—0
GASS: Generalizing Audio Source Separation with Large-scale Data—0
A Generalized Bandsplit Neural Network for Cinematic Audio Source SeparationCode1
Separate Anything You DescribeCode3
Language-Guided Audio-Visual Source Separation via Trimodal Consistency—0
Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation—0
Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks—0
Hyperbolic Audio Source Separation—0
Differentiable Dictionary Search: Integrating Linear Mixing with Deep Non-Linear Modelling for Audio Source Separation—0
Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source SeparationCode0
Show:102550
← PrevPage 3 of 12Next →
All datasetsAudioSetMUSIC (multi-source)

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ST-SED-SEPSDR10.55—Unverified
2Co-SeparationSDR4.26—Unverified
#ModelMetricClaimedVerifiedStatus
1Co-SeparationSAR11.3—Unverified