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 51–100 of 107 papers

TitleStatusHype
Distortion Audio Effects: Learning How to Recover the Clean Signal—0
Unsupervised Music Source Separation Using Differentiable Parametric Source ModelsCode1
CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNetCode1
Danna-Sep: Unite to separate them allCode1
Transfer Learning with Jukebox for Music Source SeparationCode1
KUIELab-MDX-Net: A Two-Stream Neural Network for Music DemixingCode1
Upsampling layers for music source separation—0
Hybrid Spectrogram and Waveform Source SeparationCode0
Unsupervised Source Separation via Bayesian Inference in the Latent DomainCode1
Music Demixing Challenge 2021Code1
A Unified Model for Zero-shot Music Source Separation, Transcription and SynthesisCode1
Multi-Task Audio Source SeparationCode1
A Hands-on Comparison of DNNs for Dialog Separation Using Transfer Learning from Music Source Separation—0
Sampling-Frequency-Independent Audio Source Separation Using Convolution Layer Based on Impulse Invariant MethodCode0
A cappella: Audio-visual Singing Voice SeparationCode1
HTMD-Net: A Hybrid Masking-Denoising Approach to Time-Domain Monaural Singing Voice Separation—0
Music source separation conditioned on 3D point cloudsCode0
Adversarial Unsupervised Domain Adaptation for Harmonic-Percussive Source Separation—0
Source Separation and Depthwise Separable Convolutions for Computer Audition—0
Densely connected multidilated convolutional networks for dense prediction tasksCode0
A Study of Transfer Learning in Music Source Separation—0
LaSAFT: Latent Source Attentive Frequency Transformation for Conditioned Source SeparationCode1
Transcription Is All You Need: Learning to Separate Musical Mixtures with Score as Supervision—0
Fast accuracy estimation of deep learning based multi-class musical source separation—0
All for One and One for All: Improving Music Separation by Bridging NetworksCode2
D3Net: Densely connected multidilated DenseNet for music source separationCode0
A frugal approach to music source separation—0
Mixing-Specific Data Augmentation Techniques for Improved Blind Violin/Piano Source SeparationCode1
Multitask learning for instrument activation aware music source separation—0
Depthwise Separable Convolutions Versus Recurrent Neural Networks for Monaural Singing Voice Separation—0
Multi-channel U-Net for Music Source SeparationCode1
Voice and accompaniment separation in music using self-attention convolutional neural network—0
Unsupervised Interpretable Representation Learning for Singing Voice SeparationCode1
Meta-learning Extractors for Music Source SeparationCode1
Time-Domain Audio Source Separation Based on Wave-U-Net Combined with Discrete Wavelet TransformCode1
Music Source Separation in the Waveform DomainCode0
Spleeter: A Fast And State-of-the Art Music Source Separation Tool With Pre-trained ModelsCode1
Bootstrapping deep music separation from primitive auditory grouping principles—0
Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity—0
Sams-Net: A Sliced Attention-based Neural Network for Music Source SeparationCode0
Open-Unmix - A Reference Implementation for Music Source SeparationCode0
Demucs: Deep Extractor for Music Sources with extra unlabeled data remixedCode0
Dilated Convolution with Dilated GRU for Music Source Separation—0
Examining the Mapping Functions of Denoising Autoencoders in Singing Voice Separation—0
Spectrogram Feature Losses for Music Source Separation—0
Semi-Supervised Monaural Singing Voice Separation With a Masking Network Trained on Synthetic MixturesCode0
Class-conditional embeddings for music source separation—0
End-to-End Sound Source Separation Conditioned On Instrument Labels—0
End-to-end music source separation: is it possible in the waveform domain?Code1
Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech SeparationCode3
Show:102550
← PrevPage 2 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
5SCNetSDR (avg)9—Unverified
6Hybrid Transformer Demucs (f.t.)SDR (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