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 1–25 of 112 papers

TitleStatusHype
Separate Anything You DescribeCode3
A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four StemsCode2
Training-Free Multi-Step Audio Source SeparationCode2
Transfer Learning with Jukebox for Music Source SeparationCode1
Time-Domain Audio Source Separation Based on Wave-U-Net Combined with Discrete Wavelet TransformCode1
Leveraging LLM and Text-Queried Separation for Noise-Robust Sound Event DetectionCode1
Spectral Mapping of Singing Voices: U-Net-Assisted Vocal SegmentationCode1
Multi-Task Audio Source SeparationCode1
Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual SupportCode1
Separate What You Describe: Language-Queried Audio Source SeparationCode1
The Cone of Silence: Speech Separation by LocalizationCode1
AutoClip: Adaptive Gradient Clipping for Source Separation NetworksCode1
Differentiable Model Compression via Pseudo Quantization NoiseCode1
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
Directional Sparse Filtering using Weighted Lehmer Mean for Blind Separation of Unbalanced Speech MixturesCode1
Hybrid Neural Networks for On-device Directional HearingCode1
Deep Audio Waveform PriorCode1
Parallel and Flexible Sampling from Autoregressive Models via Langevin DynamicsCode1
Facing the Music: Tackling Singing Voice Separation in Cinematic Audio Source SeparationCode1
OtoWorld: Towards Learning to Separate by Learning to MoveCode1
Sudo rm -rf: Efficient Networks for Universal Audio Source SeparationCode1
The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World SoundtracksCode1
Unified Gradient Reweighting for Model Biasing with Applications to Source SeparationCode1
Show:102550
← PrevPage 1 of 5Next →
All datasetsAudioSetMUSIC (multi-source)

Benchmark Results

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