Discriminative Latent Representations for Robust GAN-Based Speech Enhancement in 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 impact of integrating discriminative latent representations on the robustness and perceptual quality scores of GAN-based speech enhancement in extremely noisy environments?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.7/10.