Speech recognition features for EEG signal description in detection of neonatal seizures

Research output: Chapter in Book/Report/Conference proceedingsConference proceedingpeer-review

Abstract

In this work, features which are usually employed in automatic speech recognition (ASR) are used for the detection of neonatal seizures in newborn EEG. Three conventional ASR feature sets are compared to the feature set which has been previously developed for this task. The results indicate that the thoroughly-studied spectral envelope based ASR features perform reasonably well on their own. Additionally, the SVM Recursive Feature Elimination routine is applied to all extracted features pooled together. It is shown that ASR features consistently appear among the top-rank features.

Original languageEnglish
Title of host publication2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
Pages3281-3284
Number of pages4
DOIs
Publication statusPublished - 2010
Event2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10 - Buenos Aires, Argentina
Duration: 31 Aug 20104 Sep 2010

Publication series

Name2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10

Conference

Conference2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
Country/TerritoryArgentina
CityBuenos Aires
Period31/08/104/09/10

Fingerprint

Dive into the research topics of 'Speech recognition features for EEG signal description in detection of neonatal seizures'. Together they form a unique fingerprint.

Cite this