arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.05459eess.SP
收藏

谱图零点的无监督分类

Unsupervised classification of the spectrogram zeros

Juan M. Miramont, François Auger, Marcelo A. Colominas, Nils Laurent, Sylvain Meignen

摘要:

频谱图的零点已被证明是描述信号的时频结构的相关特征,其起源于时频平面中的分量之间的相消干涉。在这项工作中,这些零的三种类型的分类介绍,根据干扰产生它们的组件的性质。回声噪声辅助的方法,提出了一种分类算法的基础上增加独立的噪声实现建立一个二维直方图描述的稳定性的零点。从该直方图中提取的特征稍后用于使用非监督聚类算法对零进行分类。本文还介绍了一种基于谱图零点分类的去噪方法。零的分类的例子给出了合成和真实的信号,以及所提出的去噪算法与另一种基于零的方法的性能比较。

英文摘要:

The zeros of the spectrogram have proven to be a relevant feature to describe the time-frequency structure of a signal, originated by the destructive interference between components in the time-frequency plane. In this work, a classification of these zeros in three types is introduced, based on the nature of the components that interfere to produce them. Echoing noise-assisted methods, a classification algorithm is proposed based on the addition of independent noise realizations to build a 2D histogram describing the stability of zeros. Features extracted from this histogram are later used to classify the zeros using a non-supervised clusterization algorithm. A denoising approach based on the classification of the spectrogram zeros is also introduced. Examples of the classification of zeros are given for synthetic and real signals, as well as a performance comparison of the proposed denoising algorithm with another zero-based approach.

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。

↑