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

Author

Temko, A. ; Boylan, G. ; Marnane, W. ; Lightbody, G.

Author_Institution

Dept. of Electr. & Electron. Eng., Univ. Coll. Cork, Cork, Ireland

fYear

2010

fDate

Aug. 31 2010-Sept. 4 2010

Firstpage

3281

Lastpage

3284

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.

Keywords

electroencephalography; feature extraction; medical disorders; medical signal processing; paediatrics; speech recognition; support vector machines; EEG signal description; SVM Recursive Feature Elimination routine; automatic speech recognition; neonatal seizure detection; speech recognition features; Cepstral analysis; Electroencephalography; Feature extraction; Filtering theory; Pediatrics; Speech recognition; Support vector machines; Algorithms; Artificial Intelligence; Diagnosis, Computer-Assisted; Electroencephalography; Epilepsy, Benign Neonatal; Female; Humans; Infant, Newborn; Male; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Speech Production Measurement;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society (EMBC), 2010 Annual International Conference of the IEEE

Conference_Location

Buenos Aires

ISSN

1557-170X

Print_ISBN

978-1-4244-4123-5

Type

conf

DOI

10.1109/IEMBS.2010.5627260

Filename

5627260