Speak without talking

Summary

People who suffer from neurological disorders that impair their ability to speak and write (such as ALS or brainstem stroke) are left behind in the current age of Information and Communication. To reduce this gap, new solutions are needed to reinstate communication capabilities. Brain-Computer Interfaces (BCI’s) promise to offer a completely new avenue towards helping people with motor disabilities to communicate and interact with their environment. The general goal of BCI research is to connect the brain directly to a computer, and thereby bypass the non-functional nerve system. The best results are obtained with implanted systems, and technologies are advancing to reduce the surgery, making the solution more accessible. Current strategies focus on a particular part of the brain, the hand region of the motor cortex, where attempted hand movements are accompanied by patterns of neuronal activity that can be detected and distinguished from each other. For people with an inability to speak or write, the hand region is not the most logical region. Translating silent speech to a speech computer would be a much more intuitive and effective way of communicating. In this project we investigate whether silently spoken words can be detected and discriminated from a region representing the facial muscles. Prior work has suggested feasibility of this, but the aim of extracting words for BCI has not been explored. With the results of this project, we intend to have sufficient evidence to provide people with severe paralysis with implantable BCI’s for communication by silent speech.

Details

Project number

406.18.GO.086

Main applicant

Prof. dr. N.F. Ramsey

Affiliated with

Universiteit Utrecht, Universitair Medisch Centrum Utrecht, Brain Center Rudolf Magnus

Team members

F.D. Fernandes

Duration

01/09/2019 to 31/08/2023