Noise-aware Speech Enhancement using Diffusion Probabilistic Model

TL;DR

This paper introduces a noise-aware diffusion-based speech enhancement method that leverages noise classification to improve performance on unseen noises, demonstrating its effectiveness across various models.

Contribution

It proposes a noise classification guided diffusion model for speech enhancement, enhancing noise specificity and generalization to unseen noises.

Findings

Improves speech enhancement performance on unseen noises.

Enhances multiple diffusion SE models with a plug-and-play module.

Shows significant gains on VB-DEMAND dataset.

Abstract

With recent advances of diffusion model, generative speech enhancement (SE) has attracted a surge of research interest due to its great potential for unseen testing noises. However, existing efforts mainly focus on inherent properties of clean speech, underexploiting the varying noise information in real world. In this paper, we propose a noise-aware speech enhancement (NASE) approach that extracts noise-specific information to guide the reverse process in diffusion model. Specifically, we design a noise classification (NC) model to produce acoustic embedding as a noise conditioner to guide the reverse denoising process. Meanwhile, a multi-task learning scheme is devised to jointly optimize SE and NC tasks to enhance the noise specificity of conditioner. NASE is shown to be a plug-and-play module that can be generalized to any diffusion SE models. Experiments on VB-DEMAND dataset show that NASE effectively improves multiple mainstream diffusion SE models, especially on unseen noises.