ABSTRACT
People that cannot communicate due to neurological disorders would bene t from an internal speech decoder. Here, we showed the ability to classify individual words during imagined speech from electrocorticographic signals. In a word imagery task, we used high gamma (70–150 Hz) time features with a support vector machine model to classify individual words from a pair of words. To account for temporal irregularities during speech production, we introduced a non-linear time alignment into the SVM kernel. Classi cation accuracy reached 88% in a two-class classi cation framework (50% chance level), and average classi cation accuracy across fteen word-pairs was signi cant across ve subjects (mean = 58%; p < 0.05). We also compared classi cation accuracy between imagined speech, overt speech and listening. As predicted, higher classi cation accuracy was obtained in the listening and overt speech conditions (mean = 89% and 86%, respectively; p < 0.0001), where speech stimuli were directly presented. The results provide evidence for a neural representation for imagined words in the temporal lobe, frontal lobe and sensorimotor cortex, consistent with previous ndings in speech perception and production. These data represent a proof of concept study for basic decoding of speech imagery, and delineate a number of key challenges to usage of speech imagery neural representations for clinical applications.
AUTHORS
Stéphanie Martin
Peter Brunner
Iñaki Iturrate
José del R. Millán
Gerwin Schalk
Robert T. Knight
Brian Pasley
Date: 2016
DOI: 10.1038/srep25803