Improvement of speech recognition by nonlinear noise reduction

Simple item page
dc.creatorUrbanowicz, Krzysztof
dc.creatorKantz, Holger
dc.date2005-07-06
dc.date2007-05-03
dc.date.accessioned2026-07-07T08:11:13Z
dc.date.available2026-07-07T08:11:13Z
dc.descriptionThe success of nonlinear noise reduction applied to a single channel recording of human voice is measured in terms of the recognition rate of a commercial speech recognition program in comparison to the optimal linear filter. The overall performance of the nonlinear method is shown to be superior. We hence demonstrate that an algorithm which has its roots in the theory of nonlinear deterministic dynamics possesses a large potential in a realistic application.
dc.descriptionsee urbanowicz.org.pl
dc.identifierhttps://arxiv.org/abs/physics/0507044
dc.identifierhttp://arxiv.org/abs/physics/0507044
dc.identifierChaos 17, 023121 (2007) (6 pages)
dc.identifierdoi:10.1063/1.2743614
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/132050
dc.subjectData Analysis, Statistics and Probability
dc.subjectComputational Physics
dc.titleImprovement of speech recognition by nonlinear noise reduction
dc.typetext

Files

Collections

arXiv