Inferring imagined speech using EEG signals

A new approach using Riemannian manifold features

Chuong H. Nguyen, George K. Karavas, Panagiotis Artemiadis

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Objective. In this paper, we investigate the suitability of imagined speech for brain-computer interface (BCI) applications. Approach. A novel method based on covariance matrix descriptors, which lie in Riemannian manifold, and the relevance vector machines classifier is proposed. The method is applied on electroencephalographic (EEG) signals and tested in multiple subjects. Main results. The method is shown to outperform other approaches in the field with respect to accuracy and robustness. The algorithm is validated on various categories of speech, such as imagined pronunciation of vowels, short words and long words. The classification accuracy of our methodology is in all cases significantly above chance level, reaching a maximum of 70% for cases where we classify three words and 95% for cases of two words. Significance. The results reveal certain aspects that may affect the success of speech imagery classification from EEG signals, such as sound, meaning and word complexity. This can potentially extend the capability of utilizing speech imagery in future BCI applications. The dataset of speech imagery collected from total 15 subjects is also published.

Original languageEnglish (US)
Article number016002
JournalJournal of Neural Engineering
Volume15
Issue number1
DOIs
StatePublished - Feb 1 2018

Fingerprint

Imagery (Psychotherapy)
Brain-Computer Interfaces
Brain computer interface
Covariance matrix
Classifiers
Acoustic waves

Keywords

  • BCI
  • EEG
  • relevance vector machines
  • speech imagery

ASJC Scopus subject areas

  • Biomedical Engineering
  • Cellular and Molecular Neuroscience

Cite this

Inferring imagined speech using EEG signals : A new approach using Riemannian manifold features. / Nguyen, Chuong H.; Karavas, George K.; Artemiadis, Panagiotis.

In: Journal of Neural Engineering, Vol. 15, No. 1, 016002, 01.02.2018.

Research output: Contribution to journalArticle

@article{a3c38c603fc047cfa7913575ae828fa1,
title = "Inferring imagined speech using EEG signals: A new approach using Riemannian manifold features",
abstract = "Objective. In this paper, we investigate the suitability of imagined speech for brain-computer interface (BCI) applications. Approach. A novel method based on covariance matrix descriptors, which lie in Riemannian manifold, and the relevance vector machines classifier is proposed. The method is applied on electroencephalographic (EEG) signals and tested in multiple subjects. Main results. The method is shown to outperform other approaches in the field with respect to accuracy and robustness. The algorithm is validated on various categories of speech, such as imagined pronunciation of vowels, short words and long words. The classification accuracy of our methodology is in all cases significantly above chance level, reaching a maximum of 70{\%} for cases where we classify three words and 95{\%} for cases of two words. Significance. The results reveal certain aspects that may affect the success of speech imagery classification from EEG signals, such as sound, meaning and word complexity. This can potentially extend the capability of utilizing speech imagery in future BCI applications. The dataset of speech imagery collected from total 15 subjects is also published.",
keywords = "BCI, EEG, relevance vector machines, speech imagery",
author = "Nguyen, {Chuong H.} and Karavas, {George K.} and Panagiotis Artemiadis",
year = "2018",
month = "2",
day = "1",
doi = "10.1088/1741-2552/aa8235",
language = "English (US)",
volume = "15",
journal = "Journal of Neural Engineering",
issn = "1741-2560",
publisher = "IOP Publishing Ltd.",
number = "1",

}

TY - JOUR

T1 - Inferring imagined speech using EEG signals

T2 - A new approach using Riemannian manifold features

AU - Nguyen, Chuong H.

AU - Karavas, George K.

AU - Artemiadis, Panagiotis

PY - 2018/2/1

Y1 - 2018/2/1

N2 - Objective. In this paper, we investigate the suitability of imagined speech for brain-computer interface (BCI) applications. Approach. A novel method based on covariance matrix descriptors, which lie in Riemannian manifold, and the relevance vector machines classifier is proposed. The method is applied on electroencephalographic (EEG) signals and tested in multiple subjects. Main results. The method is shown to outperform other approaches in the field with respect to accuracy and robustness. The algorithm is validated on various categories of speech, such as imagined pronunciation of vowels, short words and long words. The classification accuracy of our methodology is in all cases significantly above chance level, reaching a maximum of 70% for cases where we classify three words and 95% for cases of two words. Significance. The results reveal certain aspects that may affect the success of speech imagery classification from EEG signals, such as sound, meaning and word complexity. This can potentially extend the capability of utilizing speech imagery in future BCI applications. The dataset of speech imagery collected from total 15 subjects is also published.

AB - Objective. In this paper, we investigate the suitability of imagined speech for brain-computer interface (BCI) applications. Approach. A novel method based on covariance matrix descriptors, which lie in Riemannian manifold, and the relevance vector machines classifier is proposed. The method is applied on electroencephalographic (EEG) signals and tested in multiple subjects. Main results. The method is shown to outperform other approaches in the field with respect to accuracy and robustness. The algorithm is validated on various categories of speech, such as imagined pronunciation of vowels, short words and long words. The classification accuracy of our methodology is in all cases significantly above chance level, reaching a maximum of 70% for cases where we classify three words and 95% for cases of two words. Significance. The results reveal certain aspects that may affect the success of speech imagery classification from EEG signals, such as sound, meaning and word complexity. This can potentially extend the capability of utilizing speech imagery in future BCI applications. The dataset of speech imagery collected from total 15 subjects is also published.

KW - BCI

KW - EEG

KW - relevance vector machines

KW - speech imagery

UR - http://www.scopus.com/inward/record.url?scp=85040688289&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040688289&partnerID=8YFLogxK

U2 - 10.1088/1741-2552/aa8235

DO - 10.1088/1741-2552/aa8235

M3 - Article

VL - 15

JO - Journal of Neural Engineering

JF - Journal of Neural Engineering

SN - 1741-2560

IS - 1

M1 - 016002

ER -