Latent-Conditioned GAN vs. Diffusion-Based Speech Enhancement Scaling in Low-SNR Conditions

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 do latent-conditioned GAN-based speech enhancement models scale in terms of perceptual evaluation (e.g., MOS scores) when trained on larger datasets compared to diffusion-based approaches in low-SNR conditions?

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