Skip to content
DraconiticResearch
Search Sources API
197,783 studies31 sourcesUpdated 49 min ago
Peer-reviewedCC BYNeuroImage

Decoding spatial attention in the cocktail party problem using whole-head high-density fNIRS

  • Sudan Duwadi1
  • De’Ja Rogers2
  • Alex D. Boyd2
  • Laura B. Carlton2
  • Yiwen Zhang2
  • Anna Kawai Gaona2
  • Aneesa Diya Pathiyaparambath2
  • Ravin Chaudhury2
  • Grace Magee2
  • Bernhard B Zimmermann2
  • Walker J O'Brien2
  • Alexander von Lühmann3
3 more authors
  • David A. Boas2
  • Meryem A. Yücel2
  • Kamal Sen1
  1. 1Neurophotonics Center, Department of Biomedical Engineering, Boston University, USA; Corresponding authors.
  2. 2Neurophotonics Center, Department of Biomedical Engineering, Boston University, USA
  3. 3Intelligent Biomedical Sensing (IBS) Lab, Machine Learning Department, Technical University of Berlin, Berlin, 10587, Germany; BIFOLD – Berlin Institute for the Foundations of Learning and Data, Berlin, 10587, Germany
Read full textDOICite

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.

Related

  1. OpenDvM: Decoding the Visual Mind — A Unified Toolbox for EEG Attention Research
    Dirk van Moorselaar, Sebastiaan Mathot, Stefan van der Stigchel
    PsyArXivPreprintCC0Full textNeuroscienceOSF
  2. Decoding motor imagery EEG signals by a deep learning network integrating multiscale filtering and temporal-channel attention mechanisms
    Yong Zhu, Yongge Shi, Jianhua Wu +1
    PLOS OnePeer-reviewedCC BYFull textNeurosciencePLOSEurope PMC
  3. Menstrual cycle and hormonal contraceptive intake alter the electrophysiological signature of selective auditory spatial attention
    M.-C. Schlueter, M. Pinnow, M. Bruene +1
    bioRxivPreprintAll rights reservedFull textNeurosciencebioRxiv
  4. VAD-EmotionNet: a spatial-spectral attention network for EEG emotion recognition in the 3D affective space
    Xiujun Li, Shen Yan, Dan Tong +2
    Cognitive NeurodynamicsPeer-reviewedLicence not statedFull textNeurosciencePMC
  5. A Complementary Dual-Branch Receptive Field Network for Cross-Channel-Density Motor Imagery EEG Decoding.
    Mengnan Zhu, Kendi Li, Junbiao Zhu +4
    Biomimetics (Basel, Switzerland)Peer-reviewedCC BYFull textNeuroscienceEurope PMC

Cite

BibTeXRIS
BibTeX
@article{duwadi2026decoding,
  title = {{Decoding spatial attention in the cocktail party problem using whole-head high-density fNIRS}},
  author = {Sudan Duwadi and De’Ja Rogers and Alex D. Boyd and Laura B. Carlton and Yiwen Zhang and Anna Kawai Gaona and Aneesa Diya Pathiyaparambath and Ravin Chaudhury and Grace Magee and Bernhard B Zimmermann and Walker J O'Brien and Alexander von Lühmann and David A. Boas and Meryem A. Yücel and Kamal Sen},
  journal = {NeuroImage},
  year = {2026},
  month = oct,
  doi = {10.1016/j.neuroimage.2026.122292},
  url = {https://doi.org/10.1016/j.neuroimage.2026.122292},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Decoding spatial attention in the cocktail party problem using whole-head high-density fNIRS
AU  - Sudan Duwadi
AU  - De’Ja Rogers
AU  - Alex D. Boyd
AU  - Laura B. Carlton
AU  - Yiwen Zhang
AU  - Anna Kawai Gaona
AU  - Aneesa Diya Pathiyaparambath
AU  - Ravin Chaudhury
AU  - Grace Magee
AU  - Bernhard B Zimmermann
AU  - Walker J O'Brien
AU  - Alexander von Lühmann
AU  - David A. Boas
AU  - Meryem A. Yücel
AU  - Kamal Sen
PY  - 2026
DA  - 2026/10/30
JO  - NeuroImage
DO  - 10.1016/j.neuroimage.2026.122292
UR  - https://doi.org/10.1016/j.neuroimage.2026.122292
AB  - 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.
SN  - 1095-9572
SN  - 1053-8119
ER  -