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 1–10 of 112 papers

TitleStatusHype
Towards Reliable Objective Evaluation Metrics for Generative Singing Voice Separation ModelsCode0
DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization—0
ZeroSep: Separate Anything in Audio with Zero Training—0
Text-Queried Audio Source Separation via Hierarchical Modeling—0
Training-Free Multi-Step Audio Source SeparationCode2
Score Distillation Sampling for Audio: Source Separation, Synthesis, and Beyond—0
Automatic Identification of Samples in Hip-Hop Music via Multi-Loss Training and an Artificial Dataset—0
Study of the Performance of CEEMDAN in Underdetermined Speech Separation—0
Leveraging LLM and Text-Queried Separation for Noise-Robust Sound Event DetectionCode1
Task-Aware Unified Source Separation—0
Show:102550
← PrevPage 1 of 12Next →
All datasetsAudioSetMUSIC (multi-source)

Benchmark Results

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