Extract And Diffuse: Latent Integration For Improved Diffusion-based Speech And Vocal Enhancement

Abstract

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

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyang2024extract

Related papers

• Speech Enhancement And Dereverberation With Diffusion-based Generative Models (2022)23.51
• Investigating The Design Space Of Diffusion Models For Speech Enhancement (2023)10.07
• Single And Few-step Diffusion For Generative Speech Enhancement (2023)10.21
• Diffusion-based Signal Refiner For Speech Enhancement And Separation (2023)2.26
• Analysing Diffusion-based Generative Approaches Versus Discriminative Approaches For Speech Restoration (2022)11.39
• Cold Diffusion For Speech Enhancement (2022)11.85
• DDTSE: Discriminative Diffusion Model For Target Speech Extraction (2023)5.84
• Storm: A Diffusion-based Stochastic Regeneration Model For Speech Enhancement And Dereverberation (2022)15.43