Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

WIN Wednesday Methods Series Title and abstract to follow. 








WIN Wednesday Works In Progress Imagined speech decoding with MEG

Presented by Oiwi Parker Jones

Abstract: Recent advances in Brain Computer Interfaces (e.g. Willett et al. 2023) demonstrate the potential for restoring communication to paralysed patients using surgical recordings. But brain surgery comes with significant risks and limitations. For example, it is prohibitively difficult to acquire surgical data at scale. By contrast, there is virtually no limit to the amount of high-quality non-invasive data that can be collected in healthy volunteers. In this project, we will test the proposition that with sufficient data, and by developing and then leveraging appropriate methods in data-efficient deep learning, non-invasive approaches will be able to compete with surgical BCIs for restoring speech. In these experiments, we will focus on data collection to decode inner speech.