Skip to main content


Developing a speech brain-computer interface

Research Achievements

Developing a speech brain-computer interface

IGERT trainee Adam Koerner, under the direction of IGERT PI Virginia de Sa, has undertaken the offline classification of EEG and EMG signals associated with phoneme production in order to work towards developing a speech brain-computer interface (BCI). Each subject was presented with one of eight consonant-vowel (CV) pairs and instructed to repeat it, first using imagined motor movement and then using overt movement. Using a combination of feature extraction methods combined with a simple linear classifier, they were able to achieve significant vowel classification accuracy for both imagined and overt speech (with and without vocalization). In addition, in some subjects it was possible to classify consonant production for both imagined and overt speech. These results demonstrate that it is possible to extract discriminable information associated with speech production for a potential future application in a speech BCI. These results will be presented at BCI2010.