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 101–112 of 112 papers

TitleStatusHype
Learning to Separate Object Sounds by Watching Unlabeled VideoCode0
Generalization Challenges for Neural Architectures in Audio Source SeparationCode0
Raw Multi-Channel Audio Source Separation using Multi-Resolution Convolutional Auto-Encoders—0
Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice ExtractionCode0
Multi-Resolution Fully Convolutional Neural Networks for Monaural Audio Source Separation—0
A Generalised Directional Laplacian Distribution: Estimation, Mixture Models and Audio Source Separation—0
Convolutive Audio Source Separation using Robust ICA and an intelligent evolving permutation ambiguity solution—0
Multi-scale Multi-band DenseNets for Audio Source SeparationCode0
Audio Source Separation Using a Deep Autoencoder—0
Audio Source Separation with Discriminative Scattering Networks—0
Nonnegative Tensor Factorization for Directional Blind Audio Source Separation—0
Semi-blind Source Separation via Sparse Representations and Online Dictionary Learning—0
Show:102550
← PrevPage 3 of 3Next →
All datasetsAudioSetMUSIC (multi-source)

Benchmark Results

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