Comparison of Diffusion-Based and GAN Speech Enhancement Models on Speaker Embedding Consistency in VoxCeleb1-H under Sub-0dB SNR

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 diffusion-based speech enhancement models compare to GAN architectures in preserving speaker embedding consistency on VoxCeleb1-H under sub-0dB SNR conditions?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.1/10.