Impact of Discriminative Latent Representations on PESQ Scores in GAN-Based Speech Enhancement under 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 does the integration of discriminative latent representations impact the perceptual evaluation of speech enhancement (PESQ) scores in GAN-based models compared to diffusion priors under SNR conditions below -10dB?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 7.6/10.