Optimal selection of electrocorticographic sensors for voice activity detection

• Published in: 2014 13th International Conference on Control Automation Robotics & Vision (ICARCV) pp. 29 - 32
• Main Authors: Kanas, Vasileios G., Mporas, Iosif, Benz, Heather L., Sgarbas, Kyriakos N., Crone, Nathan E., Bezerianos, Anastasios
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2014
• Subjects: Accuracy; Brain machine interface (BMI); Decoding; electrocorticography (ECoG); Electrodes; minimal clinical risk; Sensor phenomena and characterization; Speech; Support vector machines; voice activity detection (VAD)

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 (s...