• Universal Sound Separation with Artificial Mixes - Postolache, E., Pons, J., Pascual, S., & Serrà, J. (2023, June). Adversarial Permutation Invariant Training for Universal Sound Separation. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1-5). IEEE. (https://arxiv.org/abs/2210.12108)

• Pons, J., Liu, X., Pascual, S., & Serrà, J. (2023). GASS: Generalizing Audio Source Separation with Large-scale Data. arXiv preprint arXiv:2310.00140. (https://arxiv.org/abs/2310.00140)

**• Independent Bayesian Inference with Unconditional Priors ***- Jayaram, V., & Thickstun, J. (2020, November). Source separation with deep generative priors. In International Conference on Machine Learning (pp. 4724-4735). PMLR. (https://arxiv.org/abs/2002.07942)

• Postolache, E., Mariani, G., Mancusi, M., Santilli, A., Cosmo, L., & Rodolà, E. (2023). Latent Autoregressive Source Separation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(8), 9444-9452. (https://arxiv.org/abs/2301.08562)* | | ✓ | - | - | Mixture-Unsupervised (Blind)

• Factorization Methods (ICA, NMF)

• Davies ME, James CJ. Source separation using single channel ICA. Signal Process. 2007;87(8):1819-1832. doi:10.1016/j.sigpro.2007.01.011

• Unsupervised Universal Sound Separation - Wisdom, S., Tzinis, E., Erdogan, H., Weiss, R. J., Wilson, K., & Hershey, J. R. (2020, December). Unsupervised sound separation using mixture invariant training. In Proceedings of the 34th International Conference on Neural Information Processing Systems (pp. 3846-3857). (https://arxiv.org/abs/2006.12701) | | - | ✓ | ✓ | Source Weakly-Supervised

• Universal Sound Separation with Text Conditioning and Artificial Mixes - Liu, X., Liu, H., Kong, Q., Mei, X., Zhao, J., Huang, Q., Plumbley, M., & Wang, W. (2022). Separate What You Describe: Language-Queried Audio Source Separation. Interspeech. (https://arxiv.org/abs/2203.15147)

• Independent Bayesian Inference with Conditional Priors

• Jayaram, V., & Thickstun, J. (2020, November). Source separation with deep generative priors. In International Conference on Machine Learning (pp. 4724-4735). PMLR. (https://arxiv.org/abs/2002.07942)
• Postolache, E., Mariani, G., Mancusi, M., Santilli, A., Cosmo, L., & Rodolà, E. (2023). Latent Autoregressive Source Separation. Proceedings of the AAAI Conference on Artificial Intelligence, 37(8), 9444-9452. (https://arxiv.org/abs/2301.08562) | | ✓ | - | ✓ | **Mixture Weakly-Supervised

• Blend of MixIt and Language-Queried Audio Source Separation?** | | ✓ | ✓ | - | Supervised (Coherence, No Labels), e.g., Harmonic Singing Voices:

• PIT Regression

• Sarkar, S., Benetos, E., & Sandler, M.B. (2021). Vocal Harmony Separation Using Time-Domain Neural Networks. Interspeech. (https://qmro.qmul.ac.uk/xmlui/handle/123456789/72826) | | ✓ | ✓ | ✓ | Supervised (Coherence & Labels), e.g., Labeled Music Sources:

• Regression

• Rouard, S., Massa, F., & Défossez, A. (2023, June). Hybrid transformers for music source separation. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1-5). IEEE. (https://arxiv.org/abs/2211.08553)
• Luo, Y., & Yu, J. (2022). Music source separation with band-split rnn. arXiv preprint arXiv:2209.15174. (https://arxiv.org/abs/2209.15174)

• Source-Joint Bayesian Inference

• Mariani, G., Tallini, I., Postolache, E., Mancusi, M., Cosmo, L., & Rodolà, E. (2024). Multi-Source Diffusion Models for Simultaneous Music Generation and Separation. The Twelfth International Conference on Learning Representations. https://openreview.net/forum?id=h922Qhkmx1 |