Generative speech enhancement methods based on generative adversarial networks (GANs) and diffusion models have shown promising results in various speech enhancement tasks. However, their performance in very low signal-to-noise ratio (SNR) scenarios remains under-explored and limited, as these conditions pose significant challenges to both discriminative and generative state-of-the-art methods. To address this, we propose a method that leverages latent features extracted from discriminative speech enhancement models as generic conditioning features to improve GAN-based speech enhancement. TheResearch goal: What is the impact of latent discriminative conditioning on the robustness of GAN-based speech enhancement models compared to diffusion priors in extreme noise scenarios?Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.9/10.