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 11–20 of 112 papers

TitleStatusHype
Differentiable Model Compression via Pseudo Quantization NoiseCode1
AutoClip: Adaptive Gradient Clipping for Source Separation NetworksCode1
Hybrid Neural Networks for On-device Directional HearingCode1
Compute and memory efficient universal sound source separationCode1
A Generalized Bandsplit Neural Network for Cinematic Audio Source SeparationCode1
Exploring Text-Queried Sound Event Detection with Audio Source SeparationCode1
Leveraging LLM and Text-Queried Separation for Noise-Robust Sound Event DetectionCode1
Multi-Task Audio Source SeparationCode1
Parallel and Flexible Sampling from Autoregressive Models via Langevin DynamicsCode1
Separate What You Describe: Language-Queried Audio Source SeparationCode1
Show:102550
← PrevPage 2 of 12Next →
All datasetsAudioSetMUSIC (multi-source)

Benchmark Results

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