FlowSep 2: Self-Supervised Flow Matching for Language-Queried Audio Source Separation
FlowSep 2:用于语言查询音频源分离的自监督流匹配方法
机构 * School of Computer Science and Electronic Engineering, University of Surrey(萨里大学计算机科学与电子工程学院) ; Meta Superintelligence Labs(元宇宙超级智能实验室) ; Department of Informatics, King’s College London(伦敦国王学院信息学系)
AI总结 本研究提出FlowSep2,一种结合Self-Flow与Diffusion Transformer的文本条件流匹配生成模型,用于语言查询音频源分离,在多个基准上达到SOTA性能,可有效分离重叠声源。
Comments Submission to IEEE/ACM Transactions on Audio, Speech, and Language Processing