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

TL;DR

This paper introduces GALD-SE, a diffusion-based speech enhancement method that uses anisotropic guidance to reduce computational complexity and improve robustness, achieving state-of-the-art results with fewer parameters.

Contribution

It proposes a novel anisotropic guidance approach in diffusion models that preserves clean speech clues, significantly lowering computational costs and enhancing performance in noisy conditions.

Findings

Achieves state-of-the-art speech enhancement results.

Uses only approximately 4.5 million parameters.

Performs well in highly noisy environments.

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 against various forms of noise and speech distortion. Experiments demonstrate that the proposed method achieves state-of-the-art results with only approximately 4.5 million parameters, a number significantly lower than that required by other diffusion methods. This effectively narrows the model size disparity between diffusion-based and predictive speech enhancement approaches. Additionally, the proposed method performs well in very noisy scenarios, demonstrating its potential for applications in highly challenging environments.