提出一键式语音增强方法，速度提升5倍且训练成本降40%
Compose Yourself: Average-Velocity Flow Matching for One-Step Speech Enhancement
- 用平均速度场重构生成过程，实现一步完成语音增强
- 相比传统方法采样快5倍，训练成本降低40%且音质不下降
- 适合追求高效实时语音处理的开发者与工程师
扩散模型和流匹配（FM）在语音增强（SE）中取得显著进展，但依赖多步生成导致计算开销大且易受离散化误差影响。近期的一步生成模型（如MeanFlow）通过平均速度场重构建模动态，展现出良好前景。本文提出专用于语音增强的一步流匹配框架COSE。为解决MeanFlow中雅可比-向量积（JVP）计算带来的高训练开销，我们引入速度组合恒等式，高效计算平均速度，消除昂贵计算同时保持理论一致性，并达到媲美现有方法的增强质量。在标准基准上的大量实验表明，COSE实现最高5倍的采样加速，训练成本降低40%，且未牺牲语音质量。代码已公开于https://github.com/ICDM-UESTC/COSE。
原文摘要 · Abstract (English)
Diffusion and flow matching (FM) models have achieved remarkable progress in speech enhancement (SE), yet their dependence on multi-step generation is computationally expensive and vulnerable to discretization errors. Recent advances in one-step generative modeling, particularly MeanFlow, provide a promising alternative by reformulating dynamics through average velocity fields. In this work, we present COSE, a one-step FM framework tailored for SE. To address the high training overhead of Jacobian-vector product (JVP) computations in MeanFlow, we introduce a velocity composition identity to compute average velocity efficiently, eliminating expensive computation while preserving theoretical consistency and achieving competitive enhancement quality. Extensive experiments on standard benchmarks show that COSE delivers up to 5x faster sampling and reduces training cost by 40%, all without compromising speech quality. Code is available at https://github.com/ICDM-UESTC/COSE.
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。