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 51–60 of 112 papers

TitleStatusHype
Densely Connected Multi-Dilated Convolutional Networks for Dense Prediction TasksCode0
Parallel and Flexible Sampling from Autoregressive Models via Langevin DynamicsCode1
Move2Hear: Active Audio-Visual Source Separation—0
Sampling-Frequency-Independent Audio Source Separation Using Convolution Layer Based on Impulse Invariant MethodCode0
MULTIMODAL ANALYSIS: Informed content estimation and audio source separation—0
Differentiable Model Compression via Pseudo Quantization NoiseCode1
Weakly-supervised Audio-visual Sound Source Detection and Separation—0
Compute and memory efficient universal sound source separationCode1
Music source separation conditioned on 3D point cloudsCode0
Directional Sparse Filtering using Weighted Lehmer Mean for Blind Separation of Unbalanced Speech MixturesCode1
Show:102550
← PrevPage 6 of 12Next →
All datasetsAudioSetMUSIC (multi-source)

Benchmark Results

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