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 1–50 of 112 papers

TitleStatusHype
Separate Anything You DescribeCode3
Training-Free Multi-Step Audio Source SeparationCode2
A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four StemsCode2
Separate What You Describe: Language-Queried Audio Source SeparationCode1
Hybrid Neural Networks for On-device Directional HearingCode1
Spectral Mapping of Singing Voices: U-Net-Assisted Vocal SegmentationCode1
Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source SeparationCode1
Unsupervised Audio Source Separation using Generative PriorsCode1
Leveraging LLM and Text-Queried Separation for Noise-Robust Sound Event DetectionCode1
Multi-Task Audio Source SeparationCode1
Deep Audio Waveform PriorCode1
AutoClip: Adaptive Gradient Clipping for Source Separation NetworksCode1
Transfer Learning with Jukebox for Music Source SeparationCode1
Compute and memory efficient universal sound source separationCode1
Sudo rm -rf: Efficient Networks for Universal Audio Source SeparationCode1
A Generalized Bandsplit Neural Network for Cinematic Audio Source SeparationCode1
The Cone of Silence: Speech Separation by LocalizationCode1
Unified Gradient Reweighting for Model Biasing with Applications to Source SeparationCode1
Unsupervised Source Separation By Steering Pretrained Music ModelsCode1
Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled DataCode1
The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World SoundtracksCode1
OtoWorld: Towards Learning to Separate by Learning to MoveCode1
Parallel and Flexible Sampling from Autoregressive Models via Langevin DynamicsCode1
Unsupervised Composable Representations for AudioCode1
Differentiable Model Compression via Pseudo Quantization NoiseCode1
Directional Sparse Filtering using Weighted Lehmer Mean for Blind Separation of Unbalanced Speech MixturesCode1
Exploring Text-Queried Sound Event Detection with Audio Source SeparationCode1
Facing the Music: Tackling Singing Voice Separation in Cinematic Audio Source SeparationCode1
Unsupervised Music Source Separation Using Differentiable Parametric Source ModelsCode1
Time-Domain Audio Source Separation Based on Wave-U-Net Combined with Discrete Wavelet TransformCode1
Unsupervised Source Separation via Bayesian Inference in the Latent DomainCode1
Remastering Divide and Remaster: A Cinematic Audio Source Separation Dataset with Multilingual SupportCode1
Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision—0
Fast accuracy estimation of deep learning based multi-class musical source separation—0
Blind Audio Source Separation with Minimum-Volume Beta-Divergence NMF—0
A Study of Transfer Learning in Music Source Separation—0
Differentiable Digital Signal Processing Mixture Model for Synthesis Parameter Extraction from Mixture of Harmonic Sounds—0
Differentiable Dictionary Search: Integrating Linear Mixing with Deep Non-Linear Modelling for Audio Source Separation—0
Automatic Identification of Samples in Hip-Hop Music via Multi-Loss Training and an Artificial Dataset—0
A Generalised Directional Laplacian Distribution: Estimation, Mixture Models and Audio Source Separation—0
Multi-Resolution Fully Convolutional Neural Networks for Monaural Audio Source Separation—0
Interleaved Multitask Learning for Audio Source Separation with Independent Databases—0
Independent Deeply Learned Matrix Analysis for Multichannel Audio Source Separation—0
Adversarial attacks on audio source separation—0
DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization—0
Language-Guided Audio-Visual Source Separation via Trimodal Consistency—0
Improving Universal Sound Separation Using Sound Classification—0
Improved Speech Enhancement with the Wave-U-Net—0
Audio Source Separation with Discriminative Scattering Networks—0
Hyperbolic Audio Source Separation—0
Show:102550
← PrevPage 1 of 3Next →
All datasetsAudioSetMUSIC (multi-source)

Benchmark Results

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