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

DOI

  1. Microstates as Disease and Progression Markers in Patients With Mild Cognitive Impairment

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. An in vivo Mouse Model to Investigate the Effect of Local Anesthetic Nanomedicines on Axonal Conduction and Excitability

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Computing Generalized Matrix Inverse on Spiking Neural Substrate

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. Deep Learning Based Attenuation Correction of PET/MRI in Pediatric Brain Tumor Patients: Evaluation in a Clinical Setting

    Research output: Contribution to journalJournal articleResearchpeer-review

  1. Multiway canonical correlation analysis of brain data

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Decoding the auditory brain with canonical component analysis

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Task-Modulated Cortical Representations of Natural Sound Source Categories

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. Subcortical and cortical correlates of pitch discrimination: Evidence for two levels of neuroplasticity in musicians

    Research output: Contribution to journalJournal articleResearchpeer-review

  5. Representation of pitch across spectral regions in human auditory cortex

    Research output: Contribution to conferenceConference abstract for conferenceResearchpeer-review

  • Daniel D E Wong
  • Søren A Fuglsang
  • Jens Hjortkjær
  • Enea Ceolini
  • Malcolm Slaney
  • Alain de Cheveigné
View graph of relations

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.

Original languageEnglish
JournalFrontiers in Neuroscience
Volume12
Issue number531
ISSN1662-4548
DOIs
Publication statusPublished - 7 Aug 2018

ID: 55065067