Attentional Selection in a Cocktail Party Environment Can Be Decoded from Single-Trial EEG

James A. O'Sullivan, Alan J. Power, Nima Mesgarani, Siddharth Rajaram, John J. Foxe, Barbara G. Shinn-Cunningham, Malcolm Slaney, Shihab A. Shamma, Edmund C. Lalor

Research output: Contribution to journalArticle

141 Citations (Scopus)

Abstract

How humans solve the cocktail party problem remains unknown. However, progress has been made recently thanks to the realization that cortical activity tracks the amplitude envelope of speech. This has led to the development of regression methods for studying the neurophysiology of continuous speech. One such method, known as stimulus-reconstruction, has been successfully utilized with cortical surface recordings and magnetoencephalography (MEG). However, the former is invasive and gives a relatively restricted view of processing along the auditory hierarchy, whereas the latter is expensive and rare. Thus it would be extremely useful for research in many populations if stimulus-reconstruction was effective using electroencephalography (EEG), a widely available and inexpensive technology. Here we show that single-trial (≈60 s) unaveraged EEG data can be decoded to determine attentional selection in a naturalistic multispeaker environment. Furthermore, we show a significant correlation between our EEG-based measure of attention and performance on a high-level attention task. In addition, by attempting to decode attention at individual latencies, we identify neural processing at ∼200 ms as being critical for solving the cocktail party problem. These findings open up new avenues for studying the ongoing dynamics of cognition using EEG and for developing effective and natural brain-computer interfaces.

Original languageEnglish (US)
Pages (from-to)1697-1706
Number of pages10
JournalCerebral Cortex
Volume25
Issue number7
DOIs
StatePublished - Jul 1 2015

Fingerprint

Electroencephalography
Brain-Computer Interfaces
Magnetoencephalography
Neurophysiology
Cognition
Technology
Research
Population

Keywords

  • attention
  • BCI
  • cocktail party
  • EEG
  • speech
  • stimulus-reconstruction

ASJC Scopus subject areas

  • Cellular and Molecular Neuroscience
  • Cognitive Neuroscience

Cite this

O'Sullivan, J. A., Power, A. J., Mesgarani, N., Rajaram, S., Foxe, J. J., Shinn-Cunningham, B. G., ... Lalor, E. C. (2015). Attentional Selection in a Cocktail Party Environment Can Be Decoded from Single-Trial EEG. Cerebral Cortex, 25(7), 1697-1706. https://doi.org/10.1093/cercor/bht355

Attentional Selection in a Cocktail Party Environment Can Be Decoded from Single-Trial EEG. / O'Sullivan, James A.; Power, Alan J.; Mesgarani, Nima; Rajaram, Siddharth; Foxe, John J.; Shinn-Cunningham, Barbara G.; Slaney, Malcolm; Shamma, Shihab A.; Lalor, Edmund C.

In: Cerebral Cortex, Vol. 25, No. 7, 01.07.2015, p. 1697-1706.

Research output: Contribution to journalArticle

O'Sullivan, JA, Power, AJ, Mesgarani, N, Rajaram, S, Foxe, JJ, Shinn-Cunningham, BG, Slaney, M, Shamma, SA & Lalor, EC 2015, 'Attentional Selection in a Cocktail Party Environment Can Be Decoded from Single-Trial EEG', Cerebral Cortex, vol. 25, no. 7, pp. 1697-1706. https://doi.org/10.1093/cercor/bht355
O'Sullivan JA, Power AJ, Mesgarani N, Rajaram S, Foxe JJ, Shinn-Cunningham BG et al. Attentional Selection in a Cocktail Party Environment Can Be Decoded from Single-Trial EEG. Cerebral Cortex. 2015 Jul 1;25(7):1697-1706. https://doi.org/10.1093/cercor/bht355
O'Sullivan, James A. ; Power, Alan J. ; Mesgarani, Nima ; Rajaram, Siddharth ; Foxe, John J. ; Shinn-Cunningham, Barbara G. ; Slaney, Malcolm ; Shamma, Shihab A. ; Lalor, Edmund C. / Attentional Selection in a Cocktail Party Environment Can Be Decoded from Single-Trial EEG. In: Cerebral Cortex. 2015 ; Vol. 25, No. 7. pp. 1697-1706.
@article{478fddc708fc488fbeaf4c5f6ed115b4,
title = "Attentional Selection in a Cocktail Party Environment Can Be Decoded from Single-Trial EEG",
abstract = "How humans solve the cocktail party problem remains unknown. However, progress has been made recently thanks to the realization that cortical activity tracks the amplitude envelope of speech. This has led to the development of regression methods for studying the neurophysiology of continuous speech. One such method, known as stimulus-reconstruction, has been successfully utilized with cortical surface recordings and magnetoencephalography (MEG). However, the former is invasive and gives a relatively restricted view of processing along the auditory hierarchy, whereas the latter is expensive and rare. Thus it would be extremely useful for research in many populations if stimulus-reconstruction was effective using electroencephalography (EEG), a widely available and inexpensive technology. Here we show that single-trial (≈60 s) unaveraged EEG data can be decoded to determine attentional selection in a naturalistic multispeaker environment. Furthermore, we show a significant correlation between our EEG-based measure of attention and performance on a high-level attention task. In addition, by attempting to decode attention at individual latencies, we identify neural processing at ∼200 ms as being critical for solving the cocktail party problem. These findings open up new avenues for studying the ongoing dynamics of cognition using EEG and for developing effective and natural brain-computer interfaces.",
keywords = "attention, BCI, cocktail party, EEG, speech, stimulus-reconstruction",
author = "O'Sullivan, {James A.} and Power, {Alan J.} and Nima Mesgarani and Siddharth Rajaram and Foxe, {John J.} and Shinn-Cunningham, {Barbara G.} and Malcolm Slaney and Shamma, {Shihab A.} and Lalor, {Edmund C.}",
year = "2015",
month = "7",
day = "1",
doi = "10.1093/cercor/bht355",
language = "English (US)",
volume = "25",
pages = "1697--1706",
journal = "Cerebral Cortex",
issn = "1047-3211",
publisher = "Oxford University Press",
number = "7",

}

TY - JOUR

T1 - Attentional Selection in a Cocktail Party Environment Can Be Decoded from Single-Trial EEG

AU - O'Sullivan, James A.

AU - Power, Alan J.

AU - Mesgarani, Nima

AU - Rajaram, Siddharth

AU - Foxe, John J.

AU - Shinn-Cunningham, Barbara G.

AU - Slaney, Malcolm

AU - Shamma, Shihab A.

AU - Lalor, Edmund C.

PY - 2015/7/1

Y1 - 2015/7/1

N2 - How humans solve the cocktail party problem remains unknown. However, progress has been made recently thanks to the realization that cortical activity tracks the amplitude envelope of speech. This has led to the development of regression methods for studying the neurophysiology of continuous speech. One such method, known as stimulus-reconstruction, has been successfully utilized with cortical surface recordings and magnetoencephalography (MEG). However, the former is invasive and gives a relatively restricted view of processing along the auditory hierarchy, whereas the latter is expensive and rare. Thus it would be extremely useful for research in many populations if stimulus-reconstruction was effective using electroencephalography (EEG), a widely available and inexpensive technology. Here we show that single-trial (≈60 s) unaveraged EEG data can be decoded to determine attentional selection in a naturalistic multispeaker environment. Furthermore, we show a significant correlation between our EEG-based measure of attention and performance on a high-level attention task. In addition, by attempting to decode attention at individual latencies, we identify neural processing at ∼200 ms as being critical for solving the cocktail party problem. These findings open up new avenues for studying the ongoing dynamics of cognition using EEG and for developing effective and natural brain-computer interfaces.

AB - How humans solve the cocktail party problem remains unknown. However, progress has been made recently thanks to the realization that cortical activity tracks the amplitude envelope of speech. This has led to the development of regression methods for studying the neurophysiology of continuous speech. One such method, known as stimulus-reconstruction, has been successfully utilized with cortical surface recordings and magnetoencephalography (MEG). However, the former is invasive and gives a relatively restricted view of processing along the auditory hierarchy, whereas the latter is expensive and rare. Thus it would be extremely useful for research in many populations if stimulus-reconstruction was effective using electroencephalography (EEG), a widely available and inexpensive technology. Here we show that single-trial (≈60 s) unaveraged EEG data can be decoded to determine attentional selection in a naturalistic multispeaker environment. Furthermore, we show a significant correlation between our EEG-based measure of attention and performance on a high-level attention task. In addition, by attempting to decode attention at individual latencies, we identify neural processing at ∼200 ms as being critical for solving the cocktail party problem. These findings open up new avenues for studying the ongoing dynamics of cognition using EEG and for developing effective and natural brain-computer interfaces.

KW - attention

KW - BCI

KW - cocktail party

KW - EEG

KW - speech

KW - stimulus-reconstruction

UR - http://www.scopus.com/inward/record.url?scp=84936759654&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84936759654&partnerID=8YFLogxK

U2 - 10.1093/cercor/bht355

DO - 10.1093/cercor/bht355

M3 - Article

VL - 25

SP - 1697

EP - 1706

JO - Cerebral Cortex

JF - Cerebral Cortex

SN - 1047-3211

IS - 7

ER -