TY - GEN
T1 - Speech recognition features for EEG signal description in detection of neonatal seizures
AU - Temko, A.
AU - Boylan, G.
AU - Marnane, W.
AU - Lightbody, G.
PY - 2010
Y1 - 2010
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/78650807747
U2 - 10.1109/IEMBS.2010.5627260
DO - 10.1109/IEMBS.2010.5627260
M3 - Conference proceeding
C2 - 21096614
AN - SCOPUS:78650807747
SN - 9781424441235
T3 - 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
SP - 3281
EP - 3284
BT - 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
T2 - 2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10
Y2 - 31 August 2010 through 4 September 2010
ER -