Spoken sentences decoding based on intracranial high gamma response using dynamic time warping.

In this study, we explore the discriminability of high gamma activities from speech production cortex during the overt articulation of two sentences. Neural activities were recorded from one intracranial electrode placed approximately over the posterior part of the inferior frontal gyrus. By employing a dynamic time warping (DTW) method to realign single-trial high gamma response during speech productions, averaged temporal activation patterns corresponding to the two spoken sentences were obtained. Single-trial ECoG responses were subsequently classified according to their correlations with these two temporal activation patterns. On average, 77.5% of the trials were correctly classified, which was much higher than the chance-level performance of the SVM classifier without DTW. Our preliminary results shed light on the construction of cortical speech brain-computer interfaces on the sentence level.