Classification of imagined spoken word-pairs using convolutional neural networks

Ciaran Cooney, Attila Korik, Folli Raffaella, Damien Coyle

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding


Imagined speech is gaining traction as a communicative paradigm for brain-computer-interfaces (BCI), as a growing body of research indicates the potential for decoding speech processes directly from the brain. The development of this type of direct-speech BCI has primarily considered feature extraction and machine learning approaches typical to BCI decoding. Here, we consider the potential of deep learning as a possible alternative to traditional BCI methodologies in relation to imagined speech EEG decoding. Two different convolutional neural networks (CNN) were trained on multiple imagined speech word-pairs, and their performance compared to a baseline linear discriminant analysis (LDA) classifier trained using filterbank common spatial patterns (FBCSP) features. Classifiers were trained using nested cross-validation to enable hyper-parameter optimization. Results obtained showed that the CNNs outperformed the FBCSP with average accuracies of 62.37% and 60.88% vs. 57.80% (p
Original languageEnglish
Title of host publicationProceedings of the 8th Graz Brain Computer Interface Conference 2019
EditorsGernot R Muller-Putz, Jonas C Ditz, Selina C Wriessnegger
PublisherVerlag der Technischen Universitat Graz
Number of pages6
ISBN (Print)978-3-85125-682-6
Publication statusPublished - 20 Sept 2019

Publication series

NameProceedings of the 8th Graz Brain-Computer Interface Conference 2019
PublisherVerlag der Technischen Universitat Graz

Bibliographical note

The 8th Graz BCI Conference, 2019 ; Conference date: 16-09-2019 Through 20-09-2023


  • Electroencephalogram (EEG)
  • Imagined Speech
  • Convolutional Neural Network
  • Brain-Computer Interface


Dive into the research topics of 'Classification of imagined spoken word-pairs using convolutional neural networks'. Together they form a unique fingerprint.

Cite this