GALD-SE: Guided Anisotropic Lightweight Diffusion For Efficient Speech Enhancement

Abstract

Speech enhancement is designed to enhance the intelligibility and quality of speech across diverse noise conditions. Recently, diffusion model has gained lots of attention in speech enhancement area, achieving competitive results. Current diffusion-based methods blur the signal with isotropic Gaussian noise and recover clean speech from the prior. However, these methods often suffer from a substantial computational burden. We argue that the computational inefficiency partially stems from the oversight that speech enhancement is not purely a generative task; it primarily involves noise reduction and completion of missing information, while the clean clues in the original mixture do not need to be regenerated. In this paper, we propose a method that introduces noise with anisotropic guidance during the diffusion process, allowing the neural network to preserve clean clues within noisy recordings. This approach substantially reduces computational complexity while exhibiting robustness aga

Stats

• citations2
• S2 citations—
• github stars0
• HF likes0
• heat score3.58
• arxiv keywang2024gald

Related papers

• Gdiffuse: Diffusion-based Speech Enhancement With Noise Model Guidance (2025)0.00
• Cold Diffusion For Speech Enhancement (2022)11.85
• 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
• Speech Enhancement And Dereverberation With Diffusion-based Generative Models (2022)23.51
• Diffusion-based Speech Enhancement With A Weighted Generative-supervised Learning Loss (2023)0.00
• Noise-aware Speech Enhancement Using Diffusion Probabilistic Model (2023)8.82
• Storm: A Diffusion-based Stochastic Regeneration Model For Speech Enhancement And Dereverberation (2022)15.43