Carregant...
Carregant...

Vés al contingut (premeu Retorn)

EEG signal description with spectral-envelope-based speech recognition features for detection of neonatal seizures

Autor
Temko, A.; Nadeu, C.; Marnane, W.; Boylan, G.; Lightbody, G.
Tipus d'activitat
Article en revista
Revista
IEEE transactions on information technology in biomedicine
Data de publicació
2011-11-21
Volum
15
Número
6
Pàgina inicial
839
Pàgina final
847
DOI
https://doi.org/10.1109/TITB.2011.2159805 Obrir en finestra nova
Repositori
http://hdl.handle.net/2117/16063 Obrir en finestra nova
URL
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5887420&tag=1 Obrir en finestra nova
Resum
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 forEEGanalysis.The results indicate that the ASR featureswhich model the spectral derivatives, either full-band or localized in frequency, yielded a performance improve...
Citació
Temko, A. [et al.]. EEG signal description with spectral-envelope-based speech recognition features for detection of neonatal seizures. "IEEE transactions on information technology in biomedicine", 21 Novembre 2011, vol. 15, núm. 6, p. 839-847.
Paraules clau
EEG, neonatal seizure detection, spectral envelope, spectral slope, speech recognition features
Grup de recerca
IDEAI-UPC Intelligent Data Science and Artificial Intelligence
TALP - Centre de Tecnologies i Aplicacions del Llenguatge i la Parla
VEU - Grup de Tractament de la Parla

Participants

  • Temko, Andrey A.  (autor)
  • Nadeu Camprubí, Climent  (autor)
  • Marnane, W.  (autor)
  • Boylan, G.B.  (autor)
  • Lightbody, G.  (autor)