SOTAVerified

Music Source Separation

Music source separation is the task of decomposing music into its constitutive components, e. g., yielding separated stems for the vocals, bass, and drums.

( Image credit: SigSep )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–50 of 107 papers

TitleStatusHype
Hybrid Transformers for Music Source SeparationCode5
The Whole Is Greater than the Sum of Its Parts: Improving Music Source Separation by Bridging NetworkCode4
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech SeparationCode3
A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four StemsCode2
SCNet: Sparse Compression Network for Music Source SeparationCode2
Training-Free Multi-Step Audio Source SeparationCode2
Music Source Separation Based on a Lightweight Deep Learning Framework (DTTNET: DUAL-PATH TFC-TDF UNET)Code2
All for One and One for All: Improving Music Separation by Bridging NetworksCode2
The Sound Demixing Challenge 2023 x2013 Music Demixing TrackCode2
Pre-training Music Classification Models via Music Source SeparationCode2
LaSAFT: Latent Source Attentive Frequency Transformation for Conditioned Source SeparationCode1
Music Source Separation with Generative FlowCode1
Sound Demixing Challenge 2023 Music Demixing Track Technical Report: TFC-TDF-UNet v3Code1
Spleeter: A Fast And State-of-the Art Music Source Separation Tool With Pre-trained ModelsCode1
Meta-learning Extractors for Music Source SeparationCode1
A fully differentiable model for unsupervised singing voice separationCode1
VocaLiST: An Audio-Visual Synchronisation Model for Lips and VoicesCode1
Unsupervised Source Separation via Bayesian Inference in the Latent DomainCode1
KUIELab-MDX-Net: A Two-Stream Neural Network for Music DemixingCode1
Music Source Separation with Band-split RNNCode1
Unsupervised Interpretable Representation Learning for Singing Voice SeparationCode1
Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source SeparationCode1
Unsupervised Music Source Separation Using Differentiable Parametric Source ModelsCode1
MedleyVox: An Evaluation Dataset for Multiple Singing Voices SeparationCode1
A Unified Model for Zero-shot Music Source Separation, Transcription and SynthesisCode1
End-to-end music source separation: is it possible in the waveform domain?Code1
Time-Domain Audio Source Separation Based on Wave-U-Net Combined with Discrete Wavelet TransformCode1
Quantifying Spatial Audio Quality ImpairmentCode1
CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNetCode1
SynthSOD: Developing an Heterogeneous Dataset for Orchestra Music Source SeparationCode1
Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio EffectsCode1
Multi-Task Audio Source SeparationCode1
A cappella: Audio-visual Singing Voice SeparationCode1
Music Source RestorationCode1
Mixing-Specific Data Augmentation Techniques for Improved Blind Violin/Piano Source SeparationCode1
Multi-channel U-Net for Music Source SeparationCode1
An Efficient Short-Time Discrete Cosine Transform and Attentive MultiResUNet Framework for Music Source SeparationCode1
Music Demixing Challenge 2021Code1
Danna-Sep: Unite to separate them allCode1
Transfer Learning with Jukebox for Music Source SeparationCode1
Adversarial Semi-Supervised Audio Source Separation applied to Singing Voice ExtractionCode0
Sams-Net: A Sliced Attention-based Neural Network for Music Source SeparationCode0
Score-informed Music Source Separation: Improving Synthetic-to-real Generalization in Classical MusicCode0
Densely connected multidilated convolutional networks for dense prediction tasksCode0
Sampling-Frequency-Independent Audio Source Separation Using Convolution Layer Based on Impulse Invariant MethodCode0
Semi-Supervised Monaural Singing Voice Separation With a Masking Network Trained on Synthetic MixturesCode0
Demucs: Deep Extractor for Music Sources with extra unlabeled data remixedCode0
Machine Perceptual Quality: Evaluating the Impact of Severe Lossy Compression on Audio and Image ModelsCode0
Low Latency Time Domain Multichannel Speech and Music Source SeparationCode0
Learned Compression for Compressed LearningCode0
Show:102550
← PrevPage 1 of 3Next →
All datasetsMUSDB18MUSDB18-HQSlakh2100

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Sparse HT Demucs (fine tuned)SDR (avg)9.2—Unverified
2Hybrid Transformer Demucs (f.t.)SDR (avg)9—Unverified
3Band-Split RNN (semi-sup.)SDR (avg)8.97—Unverified
4TFC-TDF-UNet (v3)SDR (avg)8.34—Unverified
5Band-Split RNNSDR (avg)8.23—Unverified
6Hybrid DemucsSDR (avg)7.72—Unverified
7KUIELab-MDX-NetSDR (avg)7.54—Unverified
8CDE-HTCNSDR (avg)6.89—Unverified
9Attentive-MultiResUNetSDR (avg)6.81—Unverified
10DEMUCS (extra)SDR (avg)6.79—Unverified
#ModelMetricClaimedVerifiedStatus
1BS-RoFormer (L=12, OA)SDR (avg)11.99—Unverified
2BS-RoFormer (L=6, OA)SDR (avg)9.8—Unverified
3SCNet-largeSDR (avg)9.69—Unverified
4Sparse HT Demucs (fine tuned)SDR (avg)9.2—Unverified
5Hybrid Transformer Demucs (f.t.)SDR (avg)9—Unverified
6SCNetSDR (avg)9—Unverified
7Band-Split RNN (semi-sup.)SDR (avg)8.97—Unverified
8TFC-TDF-UNet (v3)SDR (avg)8.34—Unverified
9Band-Split RNNSDR (avg)8.24—Unverified
10Dual-Path TFC-TDF UNet (DTTNet)SDR (avg)8.15—Unverified
#ModelMetricClaimedVerifiedStatus
1DiCoSe (Deterministic)SI-SDRi (Bass)20.04—Unverified
2LQ-VAE + Scalable TransformerSDR (bass)7.42—Unverified