Decoding the auditory brain with canonical component analysis

Alain de Cheveigné*, Daniel D E Wong, Giovanni M Di Liberto, Jens Hjortkjær, Malcolm Slaney, Edmund Lalor

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

44 Downloads (Pure)

Abstract

The relation between a stimulus and the evoked brain response can shed light on perceptual processes within the brain. Signals derived from this relation can also be harnessed to control external devices for Brain Computer Interface (BCI) applications. While the classic event-related potential (ERP) is appropriate for isolated stimuli, more sophisticated "decoding" strategies are needed to address continuous stimuli such as speech, music or environmental sounds. Here we describe an approach based on Canonical Correlation Analysis (CCA) that finds the optimal transform to apply to both the stimulus and the response to reveal correlations between the two. Compared to prior methods based on forward or backward models for stimulus-response mapping, CCA finds significantly higher correlation scores, thus providing increased sensitivity to relatively small effects, and supports classifier schemes that yield higher classification scores. CCA strips the brain response of variance unrelated to the stimulus, and the stimulus representation of variance that does not affect the response, and thus improves observations of the relation between stimulus and response.
Original languageEnglish
JournalNeuroImage
Volume172
Pages (from-to)206-216
ISSN1053-8119
DOIs
Publication statusPublished - 2018

Keywords

  • CCA
  • Canonical correlation
  • EEG
  • ICA
  • LFP
  • MEG
  • Modulation filter
  • PCA
  • Reverse correlation
  • Speech
  • TRF
  • Journal Article

Cite this

de Cheveigné, A., Wong, D. D. E., Di Liberto, G. M., Hjortkjær, J., Slaney, M., & Lalor, E. (2018). Decoding the auditory brain with canonical component analysis. NeuroImage, 172, 206-216. https://doi.org/10.1016/j.neuroimage.2018.01.033
de Cheveigné, Alain ; Wong, Daniel D E ; Di Liberto, Giovanni M ; Hjortkjær, Jens ; Slaney, Malcolm ; Lalor, Edmund. / Decoding the auditory brain with canonical component analysis. In: NeuroImage. 2018 ; Vol. 172. pp. 206-216.
@article{da3977a369d24d81ac87be0368e340e4,
title = "Decoding the auditory brain with canonical component analysis",
abstract = "The relation between a stimulus and the evoked brain response can shed light on perceptual processes within the brain. Signals derived from this relation can also be harnessed to control external devices for Brain Computer Interface (BCI) applications. While the classic event-related potential (ERP) is appropriate for isolated stimuli, more sophisticated {"}decoding{"} strategies are needed to address continuous stimuli such as speech, music or environmental sounds. Here we describe an approach based on Canonical Correlation Analysis (CCA) that finds the optimal transform to apply to both the stimulus and the response to reveal correlations between the two. Compared to prior methods based on forward or backward models for stimulus-response mapping, CCA finds significantly higher correlation scores, thus providing increased sensitivity to relatively small effects, and supports classifier schemes that yield higher classification scores. CCA strips the brain response of variance unrelated to the stimulus, and the stimulus representation of variance that does not affect the response, and thus improves observations of the relation between stimulus and response.",
keywords = "CCA, Canonical correlation, EEG, ICA, LFP, MEG, Modulation filter, PCA, Reverse correlation, Speech, TRF, Journal Article",
author = "{de Cheveign{\'e}}, Alain and Wong, {Daniel D E} and {Di Liberto}, {Giovanni M} and Jens Hjortkj{\ae}r and Malcolm Slaney and Edmund Lalor",
year = "2018",
doi = "10.1016/j.neuroimage.2018.01.033",
language = "English",
volume = "172",
pages = "206--216",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Elsevier",

}

de Cheveigné, A, Wong, DDE, Di Liberto, GM, Hjortkjær, J, Slaney, M & Lalor, E 2018, 'Decoding the auditory brain with canonical component analysis', NeuroImage, vol. 172, pp. 206-216. https://doi.org/10.1016/j.neuroimage.2018.01.033

Decoding the auditory brain with canonical component analysis. / de Cheveigné, Alain; Wong, Daniel D E; Di Liberto, Giovanni M; Hjortkjær, Jens; Slaney, Malcolm; Lalor, Edmund.

In: NeuroImage, Vol. 172, 2018, p. 206-216.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Decoding the auditory brain with canonical component analysis

AU - de Cheveigné, Alain

AU - Wong, Daniel D E

AU - Di Liberto, Giovanni M

AU - Hjortkjær, Jens

AU - Slaney, Malcolm

AU - Lalor, Edmund

PY - 2018

Y1 - 2018

N2 - The relation between a stimulus and the evoked brain response can shed light on perceptual processes within the brain. Signals derived from this relation can also be harnessed to control external devices for Brain Computer Interface (BCI) applications. While the classic event-related potential (ERP) is appropriate for isolated stimuli, more sophisticated "decoding" strategies are needed to address continuous stimuli such as speech, music or environmental sounds. Here we describe an approach based on Canonical Correlation Analysis (CCA) that finds the optimal transform to apply to both the stimulus and the response to reveal correlations between the two. Compared to prior methods based on forward or backward models for stimulus-response mapping, CCA finds significantly higher correlation scores, thus providing increased sensitivity to relatively small effects, and supports classifier schemes that yield higher classification scores. CCA strips the brain response of variance unrelated to the stimulus, and the stimulus representation of variance that does not affect the response, and thus improves observations of the relation between stimulus and response.

AB - The relation between a stimulus and the evoked brain response can shed light on perceptual processes within the brain. Signals derived from this relation can also be harnessed to control external devices for Brain Computer Interface (BCI) applications. While the classic event-related potential (ERP) is appropriate for isolated stimuli, more sophisticated "decoding" strategies are needed to address continuous stimuli such as speech, music or environmental sounds. Here we describe an approach based on Canonical Correlation Analysis (CCA) that finds the optimal transform to apply to both the stimulus and the response to reveal correlations between the two. Compared to prior methods based on forward or backward models for stimulus-response mapping, CCA finds significantly higher correlation scores, thus providing increased sensitivity to relatively small effects, and supports classifier schemes that yield higher classification scores. CCA strips the brain response of variance unrelated to the stimulus, and the stimulus representation of variance that does not affect the response, and thus improves observations of the relation between stimulus and response.

KW - CCA

KW - Canonical correlation

KW - EEG

KW - ICA

KW - LFP

KW - MEG

KW - Modulation filter

KW - PCA

KW - Reverse correlation

KW - Speech

KW - TRF

KW - Journal Article

U2 - 10.1016/j.neuroimage.2018.01.033

DO - 10.1016/j.neuroimage.2018.01.033

M3 - Journal article

VL - 172

SP - 206

EP - 216

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

ER -