Investigating The Design Space Of Diffusion Models For Speech Enhancement

Abstract

Diffusion models are a new class of generative models that have shown outstanding performance in image generation literature. As a consequence, studies have attempted to apply diffusion models to other tasks, such as speech enhancement. A popular approach in adapting diffusion models to speech enhancement consists in modelling a progressive transformation between the clean and noisy speech signals. However, one popular diffusion model framework previously laid in image generation literature did not account for such a transformation towards the system input, which prevents from relating the existing diffusion-based speech enhancement systems with the aforementioned diffusion model framework. To address this, we extend this framework to account for the progressive transformation between the clean and noisy speech signals. This allows us to apply recent developments from image generation literature, and to systematically investigate design aspects of diffusion models that remain largely u

Stats

• citations21
• S2 citations—
• github stars0
• HF likes0
• heat score10.07
• arxiv keygonzalez2023investigating

Related papers

• Speech Enhancement And Dereverberation With Diffusion-based Generative Models (2022)23.51
• Cold Diffusion For Speech Enhancement (2022)11.85
• Storm: A Diffusion-based Stochastic Regeneration Model For Speech Enhancement And Dereverberation (2022)15.43
• Analysing Diffusion-based Generative Approaches Versus Discriminative Approaches For Speech Restoration (2022)11.39
• Extract And Diffuse: Latent Integration For Improved Diffusion-based Speech And Vocal Enhancement (2024)0.00
• Single And Few-step Diffusion For Generative Speech Enhancement (2023)10.21
• GALD-SE: Guided Anisotropic Lightweight Diffusion For Efficient Speech Enhancement (2024)3.58
• Diffusion-based Signal Refiner For Speech Enhancement And Separation (2023)2.26