Impact of Discriminative Latent Conditioning on GAN Adversarial Robustness Versus Diffusion Priors in Low-SNR Speech Enhancement

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: How does conditioning GAN-based speech enhancement with discriminative latents impact adversarial robustness compared to diffusion priors in low-SNR scenarios?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.8/10.