Inner Speech Classification using EEG Signals: A Deep Learning Approach

Bram van den Berg; Sander van Donkelaar; Maryam Alimardani

doi:10.1109/ICHMS53169.2021.9582457

Inner Speech Classification using EEG Signals: A Deep Learning Approach

Bram van den Berg
, Sander van Donkelaar
, Maryam Alimardani

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Brain computer interfaces (BCIs) provide a direct communication pathway between humans and computers. There are three major BCI paradigms that are commonly employed: motor-imagery (MI), event-related potential (ERP), and steady-state visually evoked potential (SSVEP). In our study, we sought to expand this by focusing on 'Inner Speech' paradigm using EEG signals. Inner Speech refers to the internalized process of imagining one's own 'voice'. Using a 2D Convolutional Neural Network (CNN) based on the EEGNet architecture, we classified the EEG signals from eight subjects when they internally thought about four different words. Our results showed an average accuracy of 29.7% for word recognition, which is slightly above chance. We discuss the limitations and provide suggestions for future research.

Original language	English
Title of host publication	2021 IEEE 2nd International Conference on Human-Machine Systems (ICHMS)
Subtitle of host publication	[Proceedings]
Editors	Andreas Nurnberger, Giancarlo Fortino, Antonio Guerrieri, David Kaber, David Mendonca, Malte Schilling, Zhiwen Yu
Publisher	Institute of Electrical and Electronics Engineers Inc.
Number of pages	4
ISBN (Electronic)	9781665401708
DOIs	https://doi.org/10.1109/ICHMS53169.2021.9582457
Publication status	Published - 2021
Externally published	Yes
Event	2021 IEEE International Conference on Human-Machine Systems, ICHMS 2021 - Magdeburg, Germany Duration: 8 Sept 2021 → 10 Sept 2021

Conference

Conference	2021 IEEE International Conference on Human-Machine Systems, ICHMS 2021
Country/Territory	Germany
City	Magdeburg
Period	8/09/21 → 10/09/21

Access to Document

10.1109/ICHMS53169.2021.9582457

Persistent URL (handle)

Persistent link

Cite this

Berg, B. V. D., Donkelaar, S. V., & Alimardani, M. (2021). Inner Speech Classification using EEG Signals: A Deep Learning Approach. In A. Nurnberger, G. Fortino, A. Guerrieri, D. Kaber, D. Mendonca, M. Schilling, & Z. Yu (Eds.), 2021 IEEE 2nd International Conference on Human-Machine Systems (ICHMS): [Proceedings] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHMS53169.2021.9582457

Berg, Bram van den ; Donkelaar, Sander van ; Alimardani, Maryam. / Inner Speech Classification using EEG Signals : A Deep Learning Approach. 2021 IEEE 2nd International Conference on Human-Machine Systems (ICHMS): [Proceedings]. editor / Andreas Nurnberger ; Giancarlo Fortino ; Antonio Guerrieri ; David Kaber ; David Mendonca ; Malte Schilling ; Zhiwen Yu. Institute of Electrical and Electronics Engineers Inc., 2021.

@inproceedings{694c7c93febf4dfd9b5627159de4d01b,

title = "Inner Speech Classification using EEG Signals: A Deep Learning Approach",

abstract = "Brain computer interfaces (BCIs) provide a direct communication pathway between humans and computers. There are three major BCI paradigms that are commonly employed: motor-imagery (MI), event-related potential (ERP), and steady-state visually evoked potential (SSVEP). In our study, we sought to expand this by focusing on 'Inner Speech' paradigm using EEG signals. Inner Speech refers to the internalized process of imagining one's own 'voice'. Using a 2D Convolutional Neural Network (CNN) based on the EEGNet architecture, we classified the EEG signals from eight subjects when they internally thought about four different words. Our results showed an average accuracy of 29.7\% for word recognition, which is slightly above chance. We discuss the limitations and provide suggestions for future research.",

author = "Berg, \{Bram van den\} and Donkelaar, \{Sander van\} and Maryam Alimardani",

year = "2021",

doi = "10.1109/ICHMS53169.2021.9582457",

language = "English",

editor = "Andreas Nurnberger and Giancarlo Fortino and Antonio Guerrieri and David Kaber and David Mendonca and Malte Schilling and Zhiwen Yu",

booktitle = "2021 IEEE 2nd International Conference on Human-Machine Systems (ICHMS)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2021 IEEE International Conference on Human-Machine Systems, ICHMS 2021 ; Conference date: 08-09-2021 Through 10-09-2021",

}

Berg, BVD, Donkelaar, SV & Alimardani, M 2021, Inner Speech Classification using EEG Signals: A Deep Learning Approach. in A Nurnberger, G Fortino, A Guerrieri, D Kaber, D Mendonca, M Schilling & Z Yu (eds), 2021 IEEE 2nd International Conference on Human-Machine Systems (ICHMS): [Proceedings]. Institute of Electrical and Electronics Engineers Inc., 2021 IEEE International Conference on Human-Machine Systems, ICHMS 2021, Magdeburg, Germany, 8/09/21. https://doi.org/10.1109/ICHMS53169.2021.9582457

Inner Speech Classification using EEG Signals: A Deep Learning Approach. / Berg, Bram van den; Donkelaar, Sander van; Alimardani, Maryam.
2021 IEEE 2nd International Conference on Human-Machine Systems (ICHMS): [Proceedings]. ed. / Andreas Nurnberger; Giancarlo Fortino; Antonio Guerrieri; David Kaber; David Mendonca; Malte Schilling; Zhiwen Yu. Institute of Electrical and Electronics Engineers Inc., 2021.

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Inner Speech Classification using EEG Signals

T2 - 2021 IEEE International Conference on Human-Machine Systems, ICHMS 2021

AU - Berg, Bram van den

AU - Donkelaar, Sander van

AU - Alimardani, Maryam

PY - 2021

Y1 - 2021

N2 - Brain computer interfaces (BCIs) provide a direct communication pathway between humans and computers. There are three major BCI paradigms that are commonly employed: motor-imagery (MI), event-related potential (ERP), and steady-state visually evoked potential (SSVEP). In our study, we sought to expand this by focusing on 'Inner Speech' paradigm using EEG signals. Inner Speech refers to the internalized process of imagining one's own 'voice'. Using a 2D Convolutional Neural Network (CNN) based on the EEGNet architecture, we classified the EEG signals from eight subjects when they internally thought about four different words. Our results showed an average accuracy of 29.7% for word recognition, which is slightly above chance. We discuss the limitations and provide suggestions for future research.

AB - Brain computer interfaces (BCIs) provide a direct communication pathway between humans and computers. There are three major BCI paradigms that are commonly employed: motor-imagery (MI), event-related potential (ERP), and steady-state visually evoked potential (SSVEP). In our study, we sought to expand this by focusing on 'Inner Speech' paradigm using EEG signals. Inner Speech refers to the internalized process of imagining one's own 'voice'. Using a 2D Convolutional Neural Network (CNN) based on the EEGNet architecture, we classified the EEG signals from eight subjects when they internally thought about four different words. Our results showed an average accuracy of 29.7% for word recognition, which is slightly above chance. We discuss the limitations and provide suggestions for future research.

UR - https://www.scopus.com/pages/publications/85118920683

U2 - 10.1109/ICHMS53169.2021.9582457

DO - 10.1109/ICHMS53169.2021.9582457

M3 - Conference contribution

BT - 2021 IEEE 2nd International Conference on Human-Machine Systems (ICHMS)

A2 - Nurnberger, Andreas

A2 - Fortino, Giancarlo

A2 - Guerrieri, Antonio

A2 - Kaber, David

A2 - Mendonca, David

A2 - Schilling, Malte

A2 - Yu, Zhiwen

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 8 September 2021 through 10 September 2021

ER -

Berg BVD, Donkelaar SV, Alimardani M. Inner Speech Classification using EEG Signals: A Deep Learning Approach. In Nurnberger A, Fortino G, Guerrieri A, Kaber D, Mendonca D, Schilling M, Yu Z, editors, 2021 IEEE 2nd International Conference on Human-Machine Systems (ICHMS): [Proceedings]. Institute of Electrical and Electronics Engineers Inc. 2021 Epub 2021 Oct 27. doi: 10.1109/ICHMS53169.2021.9582457

Inner Speech Classification using EEG Signals: A Deep Learning Approach

Abstract

Conference

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this