EEG Signal Description with Spectral-Envelope-Based Speech Recognition Features for Detection of Neonatal Seizures

• Published in: IEEE transactions on information technology in biomedicine Vol. 15; no. 6; pp. 839 - 847
• Main Authors: Temko, A., Nadeu, C., Marnane, W., Boylan, G. B., Lightbody, G.
• Format: Journal Article Publication
• Language: English
• Published: United States IEEE 01.11.2011
• Subjects: Algorithms; Automatic speech recognition; Cepstral analysis; Diagnosis, Computer-Assisted - methods; Discrete cosine transforms; EEG; Electroencephalography; Electroencephalography - methods; Feature extraction; Humans; Infant, Newborn; Infant, Newborn, Diseases - diagnosis; Informàtica; Intel·ligència artificial; Llenguatge natural; neonatal seizure detection; Pattern Recognition, Automated - methods; Pediatrics; Reconeixement automàtic de la parla; Seizures - diagnosis; Sensitivity and Specificity; Signal Processing, Computer-Assisted; spectral envelope; spectral slope; Speech Acoustics; Speech Production Measurement; Speech recognition; speech recognition features; Support vector machines; Àrees temàtiques de la UPC
• ISSN: 1089-7771; 1558-0032
• DOI: 10.1109/TITB.2011.2159805

In this paper, features which are usually employed in automatic speech recognition (ASR) are used for the detection of seizures in newborn EEG. In particular, spectral envelope-based features, composed of spectral powers and their spectral derivatives are compared to the established feature set which has been previously developed for EEG analysis. The results indicate that the ASR features which model the spectral derivatives, either full-band or localized in frequency, yielded a performance improvement, in comparison to spectral-power-based features. Indeed it is shown here that they perform reasonably well in comparison with the conventional EEG feature set. The contribution of the ASR features was analyzed here using the support vector machines (SVM) recursive feature elimination technique. It is shown that the spectral derivative features consistently appear among the top-rank features. The study shows that the ASR features should be given a high priority when dealing with the description of the EEG signal.