Feasibility of decoding covert speech in ECoG with a Transformer trained on overt speech

Several attempts for speech brain–computer interfacing (BCI) have been made to decode phonemes, sub-words, words, or sentences using invasive measurements, such as the electrocorticogram (ECoG), during auditory speech perception, overt speech, or imagined (covert) speech. Decoding sentences from covert speech is a challenging task. Sixteen epilepsy patients with intracranially implanted electrodes participated in this study, and ECoGs were recorded during overt speech, covert speech, and passive listening of eight Japanese sentences, each consisting of three tokens. A Transformer neural network model was applied to decode text sentences from covert speech, which was trained using ECoGs obtained during overt speech. We first examined the proposed Transformer model using the same task for training and testing and then evaluated the model’s performance when trained with overt or perception tasks for decoding covert speech. The Transformer model trained on covert speech achieved an average token error rate (TER) of 46.6% for decoding covert speech, whereas the model trained on overt speech achieved a comparable TER of 46.3% (p > 0.05; d = 0.07). Therefore the challenge of collecting training data for covert speech can be addressed using overt speech. The performance of covert speech can improve by using large amounts of overt speech.