Latent Discriminative Conditioning for Accelerated Convergence and Throughput in GAN-Based 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: What is the impact of latent discriminative conditioning on the convergence speed and inference throughput of GAN-based speech enhancement models relative to unconditional diffusion approaches?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.3/10.