Task-Aware Unified Source Separation

K Saijo, J Ebbers, FG Germain, G Wichern… - arXiv preprint arXiv …, 2024 - arxiv.org
Several attempts have been made to handle multiple source separation tasks such as
speech enhancement, speech separation, sound event separation, music source separation …

Universal Score-based Speech Enhancement with High Content Preservation

R Scheibler, Y Fujita, Y Shirahata… - arXiv preprint arXiv …, 2024 - arxiv.org
We propose UNIVERSE++, a universal speech enhancement method based on score-
based diffusion and adversarial training. Specifically, we improve the existing UNIVERSE …