Myungjong Kim1, Paul Ferrari2, Daragh Heitzman3, Angel Hernandez-Mulero4, Jun Wang1
11:30 - 13:30 | Fri 26 May | Emerald III, Rose, Narcissus & Jasmine | FrPS1T1.56
This project explored the possibility to decode spoken phrases from non-invasive brain activity (MEG) signals. We used dynamic time warping and Wiener filtering for noise reduction, Gamma band filtering for feature extraction, and then Gaussian mixture model and artificial neural network as the decoders. Preliminary results demonstrated the possibility of decoding speech production directly from MEG signals.