Methods Series

 Title and abstract to follow. 

 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.