用均值流实现单次计算的高效语音增强，效果远超传统生成模型。
MeanSE: Efficient Generative Speech Enhancement with Mean Flows
- 通过建模平均速度场，实现单次函数评估（1-NFE）的语音增强
- 在单次计算下性能显著优于基线流匹配模型，提升明显
- 特别适合对实时性要求高、需跨域泛化的语音处理场景
语音增强旨在改善降质语音的质量，生成式模型如流匹配因其出色的感知质量受到关注。然而，基于流的模型需要多次函数评估（NFE）才能达到稳定且满意的效果，导致计算开销大，且1-NFE性能较差。本文提出MeanSE，一种基于均值流的高效生成式语音增强模型，通过建模平均速度场，实现高质量的单次函数评估（1-NFE）增强。实验表明，所提方法在仅使用1次NFE时，显著优于流匹配基线，展现出极强的跨域泛化能力。
原文摘要 · Abstract (English)
Speech enhancement (SE) improves degraded speech's quality, with generative models like flow matching gaining attention for their outstanding perceptual quality. However, the flow-based model requires multiple numbers of function evaluations (NFEs) to achieve stable and satisfactory performance, leading to high computational load and poor 1-NFE performance. In this paper, we propose MeanSE, an efficient generative speech enhancement model using mean flows, which models the average velocity field to achieve high-quality 1-NFE enhancement. Experimental results demonstrate that our proposed MeanSE significantly outperforms the flow matching baseline with a single NFE, exhibiting extremely better out-of-domain generalization capabilities.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。