URGENT Challenge: Universality, Robustness, and Generalizability For Speech Enhancement

[Free GPT-4]
[PDF] arxiv.org

AnyEnhance: A Unified Generative Model with Prompt-Guidance and Self-Critic for Voice Enhancement

J Zhang, J Yang, Z Fang, Y Wang, Z Zhang… - arxiv preprint arxiv …, 2025 - arxiv.org
We introduce AnyEnhance, a unified generative model for voice enhancement that
processes both speech and singing voices. Based on a masked generative model …
Save Cite Related articles View as HTML
[Free GPT-4]
[PDF] arxiv.org

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 …
Save Cite Related articles View as HTML
[Free GPT-4]
[PDF] arxiv.org

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 …
Save Cite Cited by 4 Related articles View as HTML