采用时频预测模型的分布保持源分离方法
Distribution Preserving Source Separation With Time Frequency Predictive Models
AI总结:
针对现有源分离方法的感知缺陷,提出一种基于无条件生成模型与混合一致性采样的分布保持源分离方法,分离信号符合源分布,在听力测试中表现更优。
摘要:
我们提出了一种分布保持源分离方法的实例,旨在解决现有最优方法的感知缺陷。该方法使用信号源的无条件生成模型,通过从以混合信号实现为条件的分布中进行混合一致性采样来完成重构。分离后的信号遵循各自的源分布,在听力测试评估分离效果时具备优势。
英文摘要:
We provide an example of a distribution preserving source separation method, which aims at addressing perceptual shortcomings of state-of-the-art methods. Our approach uses unconditioned generative models of signal sources. Reconstruction is achieved by means of mix-consistent sampling from a distribution conditioned on a realization of a mix. The separated signals follow their respective source distributions, which provides an advantage when separation results are evaluated in a listening test.
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。