TY - GEN
T1 - Optimal selection of electrocorticographic sensors for voice activity detection
AU - Kanas, Vasileios G.
AU - Mporas, Iosif
AU - Benz, Heather L.
AU - Sgarbas, Kyriakos N.
AU - Crone, Nathan E.
AU - Bezerianos, Anastasios
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014
Y1 - 2014
N2 - An effective speech brain machine interface requires selecting the best cortical recording sites and signal features for decoding speech production, but also minimal clinical risk for the patient. Motivated by this need to reduce patient risk, the purpose of this study is to detect voice activity (speech onset and offset) automatically from spatial-spectral features of electrocorticographic signals using the optimal number of sensors (minimal invasiveness). ECoG signals were recorded while a subject performed two different syllable repetition tasks. We found that the optimal frequency resolution for detecting voice activity is 8 Hz using 31 sensors out of 55, achieving 98.2% accuracy by employing support vector machines (SVM) as a classifier, and that acceptable accuracy of 96.7% was achieved using 15 sensors, which would permit a less invasive surgery for the placement of electrodes. The proposed voice activity detector may be utilized as a part of an ECoG-based automated natural speech BMI system.
AB - An effective speech brain machine interface requires selecting the best cortical recording sites and signal features for decoding speech production, but also minimal clinical risk for the patient. Motivated by this need to reduce patient risk, the purpose of this study is to detect voice activity (speech onset and offset) automatically from spatial-spectral features of electrocorticographic signals using the optimal number of sensors (minimal invasiveness). ECoG signals were recorded while a subject performed two different syllable repetition tasks. We found that the optimal frequency resolution for detecting voice activity is 8 Hz using 31 sensors out of 55, achieving 98.2% accuracy by employing support vector machines (SVM) as a classifier, and that acceptable accuracy of 96.7% was achieved using 15 sensors, which would permit a less invasive surgery for the placement of electrodes. The proposed voice activity detector may be utilized as a part of an ECoG-based automated natural speech BMI system.
KW - Brain machine interface (BMI)
KW - electrocorticography (ECoG)
KW - minimal clinical risk
KW - voice activity detection (VAD)
UR - http://www.scopus.com/inward/record.url?scp=84949924905&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84949924905&partnerID=8YFLogxK
U2 - 10.1109/ICARCV.2014.7064274
DO - 10.1109/ICARCV.2014.7064274
M3 - Conference contribution
AN - SCOPUS:84949924905
T3 - 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014
SP - 29
EP - 32
BT - 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 13th International Conference on Control Automation Robotics and Vision, ICARCV 2014
Y2 - 10 December 2014 through 12 December 2014
ER -