Delay-Coordinates Embeddings as a Data Mining Tool for Denoising Speech Signals

Document Type


Publication Date



In this paper, we utilize techniques from the theory of nonlinear dynamical systems to define a notion of embedding estimators. More specifically, we use delay-coordinates embeddings of sets of coefficients of the measured signal (in some chosen frame) as a data mining tool to separate structures that are likely to be generated by signals belonging to some predetermined data set. We implement the embedding estimator in a windowed Fourier frame, and we apply it to speech signals heavily corrupted by white noise. Our experimental work suggests that, after training on the data sets of interest, these estimators perform well for a variety of white noise processes and noise intensity levels.


This article was originally published in Chaos: An Interdisciplinary Journal of Nonlinear Science, volume 16, in 2006. DOI: 10.1063/1.2384909

Peer Reviewed



American Institute of Physics