FlowSE：基于流匹配的语音增强
FlowSE: Flow Matching-based Speech Enhancement
AI总结：
本文提出基于条件流匹配的语音增强方法FlowSE，在极低函数评估次数（NFE为5）下即可达到传统扩散模型高NFE时的性能，且无需额外微调。
摘要：
扩散概率模型在语音增强中表现出色，但在推理阶段通常需要25到60次函数评估，导致计算复杂度过高。近期提出的一种微调方法可修正逆过程，显著降低了函数评估次数（NFE）。流匹配是一种训练连续正则化流的方法，能够建模从已知分布到未知分布的概率路径，包括由扩散过程描述的路径。本文提出一种基于条件流匹配的语音增强方法。当NFE为5时，所提方法取得了与基于扩散的语音增强在NFE为60时相当的性能；并且在1到5的相同NFE下，无需额外微调程序，便展现出与修正逆过程的扩散模型相似的性能。我们还表明，从带有改进的最优传输条件向量场的条件概率路径推导出的相应扩散模型，在NFE为5且无任何微调程序时，也表现出相似的性能。
英文摘要：
Diffusion probabilistic models have shown impressive performance for speech enhancement, but they typically require 25 to 60 function evaluations in the inference phase, resulting in heavy computational complexity. Recently, a fine-tuning method was proposed to correct the reverse process, which significantly lowered the number of function evaluations (NFE). Flow matching is a method to train continuous normalizing flows which model probability paths from known distributions to unknown distributions including those described by diffusion processes. In this paper, we propose a speech enhancement based on conditional flow matching. The proposed method achieved the performance comparable to those for the diffusion-based speech enhancement with the NFE of 60 when the NFE was 5, and showed similar performance with the diffusion model correcting the reverse process at the same NFE from 1 to 5 without additional fine tuning procedure. We also have shown that the corresponding diffusion model derived from the conditional probability path with a modified optimal transport conditional vector field demonstrated similar performances with the NFE of 5 without any fine-tuning procedure.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
