Extract and Diffuse: Latent Integration for Improved Diffusion-based Speech and Vocal Enhancement
This work addresses speech and vocal enhancement for audio processing applications, representing an incremental improvement by combining generative and discriminative models.
The paper tackled the problem of improving fidelity in diffusion-based speech and vocal enhancement by integrating latent representations from a discriminative model, achieving relative improvements of 3.7% in SI-SDR and 10.0% in SI-SIR compared to a baseline diffusion model.
Diffusion-based generative models have recently achieved remarkable results in speech and vocal enhancement due to their ability to model complex speech data distributions. While these models generalize well to unseen acoustic environments, they may not achieve the same level of fidelity as the discriminative models specifically trained to enhance particular acoustic conditions. In this paper, we propose Ex-Diff, a novel score-based diffusion model that integrates the latent representations produced by a discriminative model to improve speech and vocal enhancement, which combines the strengths of both generative and discriminative models. Experimental results on the widely used MUSDB dataset show relative improvements of 3.7% in SI-SDR and 10.0% in SI-SIR compared to the baseline diffusion model for speech and vocal enhancement tasks, respectively. Additionally, case studies are provided to further illustrate and analyze the complementary nature of generative and discriminative models in this context.