Event Abstract

Back to Event

Identifying Selective Auditory Attention to Speech from Electrocorticographic Signals

Karen Dijkstra1, 2, 3, Peter Brunner1, 2*, Aysegul Gunduz1, 4, Wiliam Coon1, 5, Anthony L. Ritaccio2, Jason Farquhar1, 2, 3, 5 and Gerwin Schalk1, 2, 5
  • 1 New York State Department of Health, Wadsworth Center, United States
  • 2 Albany Medical College, Department of Neurology, United States
  • 3 Donders Institute for Brain, Cognition and Behaviour, Department of Artificial Intelligence, Netherlands
  • 4 University of Florida, J. Crayton Pruitt Family Department of Biomedical Engineering, United States
  • 5 State University of New York at Albany, Department of Biomedical Sciences, United States

People affected by severe neuro-degenerative diseases (e.g., late-stage amyotrophic lateral sclerosis (ALS) or locked-in syndrome) eventually lose all muscular control. Thus, they cannot use traditional assistive communication devices that depend on muscle control, or brain-computer interfaces (BCIs) that depend on the ability to control gaze. Auditory and tactile BCIs are considered one of the few remaining communication options for such individuals. All currently used auditory or tactile BCIs are cumbersome to learn and use because they require the user to associate a specific arbitrary stimulus with a specific intended message. An auditory BCI would be much easier to use if a user could simply pay attention to one of several stimuli that matches his/her intent. Recent studies provided the physiological basis for such a BCI by showing that the attended speech envelope is tracked by electrocorticographic (ECoG) signals in the gamma band (i.e., 70–170 Hz). To what extent this effect may support BCI communication remains to be determined. In this study, we determined the potential communication performance of a BCI based on selective auditory attention to speech. Our results show that a single cortical location over superior temporal gyrus or pre-motor cortex is typically sufficient to identify the speech stimulus that the user attended to within 10 s and with 77% accuracy (50% accuracy due to chance). These results lay the groundwork for future studies that may determine the real-time performance of BCIs based on selective auditory attention to speech.

Keywords: Neuro-degenerative diseases, Amyotrophic lateral sclerosis (ALS), Brain-Computer Interfaces, Electrocorticographic Signals, selective auditory attention

Conference: 2015 International Workshop on Clinical Brain-Machine Interfaces (CBMI2015), Tokyo, Japan, 13 Mar - 15 Mar, 2015.

Presentation Type: Poster 2-2

Topic: Clinical Brain-Machine Interfaces

Citation: Dijkstra K, Brunner P, Gunduz A, Coon W, Ritaccio AL, Farquhar J and Schalk G (2015). Identifying Selective Auditory Attention to Speech from Electrocorticographic Signals. Conference Abstract: 2015 International Workshop on Clinical Brain-Machine Interfaces (CBMI2015). doi: 10.3389/conf.fnhum.2015.218.00025

Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters.

The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated.

Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed.

For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions.

Received: 23 Apr 2015; Published Online: 29 Apr 2015.

* Correspondence: Dr. Peter Brunner, New York State Department of Health, Wadsworth Center, Albany, NY, 12208, United States, brunner@neurotechcenter.org