Research
Print page Print page
Switch language
The Capital Region of Denmark - a part of Copenhagen University Hospital
Published

A Comparison of Regularization Methods in Forward and Backward Models for Auditory Attention Decoding

Research output: Contribution to journalJournal articleResearchpeer-review

Harvard

APA

CBE

MLA

Vancouver

Author

Wong, Daniel D E ; Fuglsang, Søren A ; Hjortkjær, Jens ; Ceolini, Enea ; Slaney, Malcolm ; de Cheveigné, Alain. / A Comparison of Regularization Methods in Forward and Backward Models for Auditory Attention Decoding. In: Frontiers in Neuroscience. 2018 ; Vol. 12, No. 531.

Bibtex

@article{ed4e4831ebef457abec79ccd00f9da78,
title = "A Comparison of Regularization Methods in Forward and Backward Models for Auditory Attention Decoding",
abstract = "The decoding of selective auditory attention from noninvasive electroencephalogram (EEG) data is of interest in brain computer interface and auditory perception research. The current state-of-the-art approaches for decoding the attentional selection of listeners are based on linear mappings between features of sound streams and EEG responses (forward model), or vice versa (backward model). It has been shown that when the envelope of attended speech and EEG responses are used to derive such mapping functions, the model estimates can be used to discriminate between attended and unattended talkers. However, the predictive/reconstructive performance of the models is dependent on how the model parameters are estimated. There exist a number of model estimation methods that have been published, along with a variety of datasets. It is currently unclear if any of these methods perform better than others, as they have not yet been compared side by side on a single standardized dataset in a controlled fashion. Here, we present a comparative study of the ability of different estimation methods to classify attended speakers from multi-channel EEG data. The performance of the model estimation methods is evaluated using different performance metrics on a set of labeled EEG data from 18 subjects listening to mixtures of two speech streams. We find that when forward models predict the EEG from the attended audio, regularized models do not improve regression or classification accuracies. When backward models decode the attended speech from the EEG, regularization provides higher regression and classification accuracies.",
author = "Wong, {Daniel D E} and Fuglsang, {S{\o}ren A} and Jens Hjortkj{\ae}r and Enea Ceolini and Malcolm Slaney and {de Cheveign{\'e}}, Alain",
year = "2018",
month = "8",
day = "7",
doi = "10.3389/fnins.2018.00531",
language = "English",
volume = "12",
journal = "Frontiers in Neuroscience",
issn = "1662-4548",
publisher = "Frontiers Research Foundation",
number = "531",

}

RIS

TY - JOUR

T1 - A Comparison of Regularization Methods in Forward and Backward Models for Auditory Attention Decoding

AU - Wong, Daniel D E

AU - Fuglsang, Søren A

AU - Hjortkjær, Jens

AU - Ceolini, Enea

AU - Slaney, Malcolm

AU - de Cheveigné, Alain

PY - 2018/8/7

Y1 - 2018/8/7

N2 - The decoding of selective auditory attention from noninvasive electroencephalogram (EEG) data is of interest in brain computer interface and auditory perception research. The current state-of-the-art approaches for decoding the attentional selection of listeners are based on linear mappings between features of sound streams and EEG responses (forward model), or vice versa (backward model). It has been shown that when the envelope of attended speech and EEG responses are used to derive such mapping functions, the model estimates can be used to discriminate between attended and unattended talkers. However, the predictive/reconstructive performance of the models is dependent on how the model parameters are estimated. There exist a number of model estimation methods that have been published, along with a variety of datasets. It is currently unclear if any of these methods perform better than others, as they have not yet been compared side by side on a single standardized dataset in a controlled fashion. Here, we present a comparative study of the ability of different estimation methods to classify attended speakers from multi-channel EEG data. The performance of the model estimation methods is evaluated using different performance metrics on a set of labeled EEG data from 18 subjects listening to mixtures of two speech streams. We find that when forward models predict the EEG from the attended audio, regularized models do not improve regression or classification accuracies. When backward models decode the attended speech from the EEG, regularization provides higher regression and classification accuracies.

AB - The decoding of selective auditory attention from noninvasive electroencephalogram (EEG) data is of interest in brain computer interface and auditory perception research. The current state-of-the-art approaches for decoding the attentional selection of listeners are based on linear mappings between features of sound streams and EEG responses (forward model), or vice versa (backward model). It has been shown that when the envelope of attended speech and EEG responses are used to derive such mapping functions, the model estimates can be used to discriminate between attended and unattended talkers. However, the predictive/reconstructive performance of the models is dependent on how the model parameters are estimated. There exist a number of model estimation methods that have been published, along with a variety of datasets. It is currently unclear if any of these methods perform better than others, as they have not yet been compared side by side on a single standardized dataset in a controlled fashion. Here, we present a comparative study of the ability of different estimation methods to classify attended speakers from multi-channel EEG data. The performance of the model estimation methods is evaluated using different performance metrics on a set of labeled EEG data from 18 subjects listening to mixtures of two speech streams. We find that when forward models predict the EEG from the attended audio, regularized models do not improve regression or classification accuracies. When backward models decode the attended speech from the EEG, regularization provides higher regression and classification accuracies.

U2 - 10.3389/fnins.2018.00531

DO - 10.3389/fnins.2018.00531

M3 - Journal article

VL - 12

JO - Frontiers in Neuroscience

JF - Frontiers in Neuroscience

SN - 1662-4548

IS - 531

ER -

ID: 55065067