Scientific Publications

DBI2 publications

Direct speech reconstruction from sensorimotor brain activity with optimized deep learning models

Type Journal
Year 2023
Author Julia Berezutskaya, Mariska van Steensel, Nick Ramsey, Marcel van Gerven
Link to publication Direct link to the publication
DOI 10.1088/1741-2552/ace8be

Development of brain-computer interface (BCI) technology is key for enabling communication in individuals who have lost the faculty of speech due to severe motor paralysis. A BCI control strategy that is gaining attention employs speech decoding from neural data. Recent studies have shown that a combination of direct neural recordings and advanced computational models can provide promising results. Understanding which decoding strategies deliver best and directly applicable results is crucial for advancing the field. In this paper, we optimized and validated a decoding approach based on speech reconstruction directly from high-density electrocorticography recordings from sensorimotor cortex during a speech production task. We show that 1) dedicated machine learning optimization of reconstruction models is key for achieving the best reconstruction performance; 2) individual word decoding in reconstructed speech achieves 92-100% accuracy (chance level is 8%); 3) direct reconstruction from sensorimotor brain activity produces intelligible speech. These results underline the need for model optimization in achieving best speech decoding results and highlight the potential that reconstruction-based speech decoding from sensorimotor cortex can offer for development of next-generation BCI technology for communication.

 

Julia Berezutskaya, Mariska van Steensel, Nick Ramsey, Marcel van Gerven
10.1088/1741-2552/ace8be
BCI, machine learning, speech reconstruction

Want to join DBI²?

Browse the vacancies page

Contact details

Radboud University
DBI2 Office
Heyendaalseweg 135
6525 AJ Nijmegen

Socials

twitter   displaying 19 gallery images for linkedin logo png 25