Dancing with Noise: Advancing Generative Speech Enhancement with Distribution Augmentation

Instead of using a standard diffusion model, most diffusion-based speech enhancement methods additionally incorporate a mean interpolation strategy into the diffusion process. However, the role and impact of this strategy remain unclear. In this study, we investigate mean interpolation from a data augmentation perspective, demonstrating that it serves as a specific form of distribution augmentation and provides a unified formula for mean interpolation, which encompasses current variations of such strategy. Building on this insight, we propose DANS (Distribution Augmentation with Noise Shuffling), an advanced distribution augmentation method that further expands the training distribution through noise-shuffling techniques. Experimental results show that DANS consistently outperforms existing methods in matched, cross-dataset, and low-data scenarios. Codes are publicly available at https://github.com/ICDM-UESTC/DANCE.