Spraak-brein-computer-interface gebaseerd op menselijke intracraniale registraties

Technology that decodes intended speech from brain activity directly could be used to bypass the impaired neural pathways of patients that are unable to vocalize speech. Initial attempts have returned impressive results when decoding brain activity during performed or perceived speech. However, to serve the needs of the speech-impaired one should aim for non-vocalized speech, also called imagined speech. A promising strategy is to transfer knowledge between speech modalities, as they share brain regions, to arrive at imagined speech decoding. This was also the objective of the proposed project. High quality neural responses were recorded directly from the cortical surface using electrocorticography and, unlike previous studies that employed only high frequency rhythms, the whole frequency spectrum is used to predict the intended speech. A proof-of-concept application was developed in which imagined speech was detected and decoded. This project aims to contribute to assistive technology to improve the quality of life of speech-impaired patients.