mlsanityData to 7 Oct 2026

Generative Adversarial Source Separation

arXiv 1710.10779 ↗First posted 30 Oct 2017cs.SD cs.LG cs.NEcited by 19

Not on the map. Why?

Abstract (arXiv)

Generative source separation methods such as non-negative matrix factorization (NMF) or auto-encoders, rely on the assumption of an output probability density. Generative Adversarial Networks (GANs) can learn data distributions without needing a parametric assumption on the output density. We show on a speech source separation experiment that, a multi-layer perceptron trained with a Wasserstein-GAN formulation outperforms NMF, auto-encoders trained with maximum likelihood, and variational auto-encoders in terms of source to distortion ratio.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 4; 2023: 4; 2024: 4; 2025: 4; 2026: 1.

19 papers.

Sort:

By area:

  1. 2023Multi-Source Diffusion Models for Simultaneous Music Generation and Separationcited by 63
  2. 2022Diffusion-based Generative Speech Source Separationcited by 41
  3. 2024Simultaneous Music Separation and Generation Using Multi-Track Latent Diffusion Modelscited by 13
  4. 2023Latent Autoregressive Source Separationcited by 12
  5. 2022Adversarial Permutation Invariant Training for Universal Sound Separationcited by 8
  6. 2025Source Separation by Flow Matchingcited by 8
  7. 2025ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Priorcited by 7
  8. 2025MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extractioncited by 4
  9. 2025User-guided Generative Source Separationcited by 2
  10. 2023Distribution Preserving Source Separation With Time Frequency Predictive Modelscited by 1
  11. 2024Improving Music Source Separation with Diffusion and Consistency Refinementcited by 1
  12. 2021Blind stain separation using model-aware generative learning and its applications on fluorescence microscopy imagescited by 0
7 more
  1. 2021One to Multiple Mapping Dual Learning: Learning Multiple Sources from One Mixed Signalcited by 0
  2. 2022Probabilistic Modelling of Signal Mixtures with Differentiable Dictionariescited by 0
  3. 2022Differentiable Dictionary Search: Integrating Linear Mixing with Deep Non-Linear Modelling for Audio Source Separationcited by 0
  4. 2023Adversarial Generative NMF for Single Channel Source Separationcited by 0
  5. 2024Maximum Discrepancy Generative Regularization and Non-Negative Matrix Factorization for Single Channel Source Separationcited by 0
  6. 2024Source Separation of Multi-source Raw Music using a Residual Quantized Variational Autoencodercited by 0
  7. 2026SURF: Separation via Unsupervised Remixing Flowcited by 0