Hiring in life sciences? Share your open positions with our professional community. Read more Close

Advertisement

Decoding Spatial Attention in the Cocktail Party Problem Using Whole-head High-Density fNIRS.

Created on 17 Oct 2026

Authors

Sudan Duwadi, De'Ja Rogers, Alex D Boyd, Laura B Carlton, Yiwen Zhang, Anna Kawai Gaona, Aneesa Diya Pathiyaparambath, Ravin Chaudhury, Grace Magee, Bernhard B Zimmermann, Walker J O'Brien, Alexander von Lühmann, David A Boas, Meryem A Yücel, Kamal Sen

Published in

NeuroImage. Pages 122292. Oct 16, 2026. Epub Oct 16, 2026.

Abstract

Spatial attention is critical for solving the cocktail party problem, a longstanding problem in neuroscience and artificial speech recognition. The ability to decode where humans are attending in a cocktail party like scene would empower applications in brain computer interfaces and assistive devices such as hearing aids. Here we demonstrate that, in an overt attention task, the attended spatial location can be decoded robustly from single trial hemodynamic responses, using a whole head high density fNIRS system. We also identify critical brain regions that make the highest contribution to decoding accuracy. Specifically, we find that decoding based on a small fraction of channels located within the left and right inferior parietal lobule (IPL) achieves maximal decoding accuracy comparable to all channels. Decoding fell close to chance in a covert auditory condition in which participants held central fixation while attending to the same talkers, indicating that auditory attention alone without orientation is not sufficient for decoding. Finally, control experiments suggest that overt-condition decoding is influenced by sustained eye position/gaze direction, not eye movement. These results support the development of fNIRS-integrated BCIs and assistive devices controlled by overt spatial attention.

PMID:
42887837
Bibliographic data and abstract were imported from PubMed on 17 Oct 2026.

Read full publication at:
Please sign in to see all details.

Advertisement

Stats

  • Community rating n/a 0 votes
  • Reviewers' rating n/a 0 votes
  • Your rating

1-terrible, 9-excellent. How would you rate this publication? Sign in in to submit your rating.

  • Recommendations n/a n/a positive of 0 vote(s)
  • Views 31
  • Comments 0

Recommended by

  • No recommendations yet.

Post a comment

You need to be signed in to post comments. You can sign in here.

Comments

There are no comments yet.

Advertisement