Adversarial Success Rates of Latent-Conditioned GANs vs. Diffusion Models in Speech Enhancement Under Extreme Noise

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. The

Research goal: What is the comparative adversarial success rate of latent-conditioned GANs versus diffusion-based speech enhancement models under extreme noise conditions?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.0/10.