{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T02:27:08Z","timestamp":1789180028009,"version":"build-2803163510"},"reference-count":25,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T00:00:00Z","timestamp":1590969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computers"],"abstract":"<jats:p>Imagined speech is a relatively new electroencephalography (EEG) neuro-paradigm, which has seen little use in Brain-Computer Interface (BCI) applications. Imagined speech can be used to allow physically impaired patients to communicate and to use smart devices by imagining desired commands and then detecting and executing those commands in a smart device. The goal of this research is to verify previous classification attempts made and then design a new, more efficient neural network that is noticeably less complex (fewer number of layers) that still achieves a comparable classification accuracy. The classifiers are designed to distinguish between EEG signal patterns corresponding to imagined speech of different vowels and words. This research uses a dataset that consists of 15 subjects imagining saying the five main vowels (a, e, i, o, u) and six different words. Two previous studies on imagined speech classifications are verified as those studies used the same dataset used here. The replicated results are compared. The main goal of this study is to take the proposed convolutional neural network (CNN) model from one of the replicated studies and make it much more simpler and less complex, while attempting to retain a similar accuracy. The pre-processing of data is described and a new CNN classifier with three different transfer learning methods is described and used to classify EEG signals. Classification accuracy is used as the performance metric. The new proposed CNN, which uses half as many layers and less complex pre-processing methods, achieved a considerably lower accuracy, but still managed to outperform the initial model proposed by the authors of the dataset by a considerable margin. It is recommended that further studies investigating classifying imagined speech should use more data and more powerful machine learning techniques. Transfer learning proved beneficial and should be used to improve the effectiveness of neural networks.<\/jats:p>","DOI":"10.3390\/computers9020046","type":"journal-article","created":{"date-parts":[[2020,6,2]],"date-time":"2020-06-02T04:09:03Z","timestamp":1591070943000},"page":"46","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":50,"title":["Classification of Vowels from Imagined Speech with Convolutional Neural Networks"],"prefix":"10.3390","volume":"9","author":[{"given":"Markus-Oliver","family":"Tamm","sequence":"first","affiliation":[{"name":"Institute of Computer Science, University of Tartu, \u00dclikooli 18, 50090 Tartu, Estonia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yar","family":"Muhammad","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, University of Tartu, \u00dclikooli 18, 50090 Tartu, Estonia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Naveed","family":"Muhammad","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, University of Tartu, \u00dclikooli 18, 50090 Tartu, Estonia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,6,1]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Edelman, B.J., Meng, J., Suma, D., Zurn, C., Nagarajan, E., Baxter, B.S., Cline, C.C., and He, B. (2019). Noninvasive neuroimaging enhances continuous neural tracking for robotic device control. Sci. Robot., 4.","DOI":"10.1126\/scirobotics.aaw6844"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1038\/s41586-019-1119-1","article-title":"Speech synthesis from neural decoding of spoken sentences","volume":"568","author":"Anumanchipalli","year":"2019","journal-title":"Nature"},{"key":"ref_3","first-page":"26","article-title":"Brain computer interface: Control signals review","volume":"223","author":"Ramadan","year":"2017","journal-title":"Neuroscience"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Puce, A., and H\u00e4m\u00e4l\u00e4inen, M.S. (2017). A review of issues related to data acquisition and analysis in EEG\/MEG studies. Brain Sci., 7.","DOI":"10.3390\/brainsci7060058"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1108\/01439911011018894","article-title":"Brain-computer interfaces: Control by thought","volume":"37","author":"Bogue","year":"2010","journal-title":"Ind. Robot. Int. J."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Cooney, C., Folli, R., and Coyle, D. (2018, January 21\u201322). Mel Frequency Cepstral Coefficients Enhance Imagined Speech Decoding Accuracy from EEG. Proceedings of the 29th Irish Signals and Systems Conference (ISSC), Belfast, UK.","DOI":"10.1109\/ISSC.2018.8585291"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Chen, W., Wang, Y., Cao, G., Chen, G., and Gu, Q. (2014). A random forest model based classification scheme for neonatal amplitude-integrated EEG. Biomed. Eng. Online, 13.","DOI":"10.1186\/1475-925X-13-S2-S4"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Cooney, C., Raffaella, F., and Coyle, D. (2019, January 6\u20139). Optimizing Input Layers Improves CNN Generalization and Transfer Learning for Imagined Speech Decoding from EEG. Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics, Bari, Italy.","DOI":"10.1109\/SMC.2019.8914246"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Roy, Y., Banville, H., Albuquerque, I., Gramfort, A., Falk, T.H., and Faubert, J. (2019). Deep learning-based electroencephalography analysis: A systematic review. J. Neural Eng., 16.","DOI":"10.1088\/1741-2552\/ab260c"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Song, Y., and Sepulveda, F. (2014, January 22\u201324). Classifying speech related vs. idle state towards onset detection in brain-computer interfaces overt, inhibited overt, and covert speech sound production vs. idle state. Proceedings of the 2014 IEEE Biomedical Circuits and Systems Conference (BioCAS), Lausanne, Switzerland.","DOI":"10.1109\/BioCAS.2014.6981789"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Zhao, S., and Rudzicz, F. (2015, January 19\u201324). Classifying phonological categories in imagined and articulated speech. Proceedings of the 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, Australia.","DOI":"10.1109\/ICASSP.2015.7178118"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1334","DOI":"10.1016\/j.neunet.2009.05.008","article-title":"Single-trial classification of vowel speech imagery using common spatial patterns","volume":"22","author":"DaSalla","year":"2009","journal-title":"Neural Netw."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Brigham, K., and Kumar, B.V.K.V. (2010, January 18\u201320). Imagined Speech Classification with EEG Signals for Silent Communication: A Preliminary Investigation into Synthetic Telepathy. Proceedings of the 2010 4th International Conference on Bioinformatics and Biomedical Engineering, Chengdu, China.","DOI":"10.1109\/ICBBE.2010.5515807"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.bspc.2018.02.021","article-title":"Automatic ocular artifacts removal in EEG using deep learning","volume":"43","author":"Yang","year":"2018","journal-title":"Biomed. Signal Process. Control."},{"key":"ref_15","unstructured":"Moctezuma, L.A., Molinas, M., Torres-Garc\u00eda, A.A., and Villase\u00f1or-Pineda, L. (2018, January 19\u201321). Towards an API for EEG-Based Imagined Speech classification. Proceedings of the International conference on Time Series and Forecasting, Granada, Spain."},{"key":"ref_16","first-page":"201","article-title":"EEG-Based discrimination of imagined speech phonemes","volume":"13","author":"Chi","year":"2011","journal-title":"Int. J. Bioelectromagn."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1016\/j.future.2019.06.027","article-title":"Deep Learning for EEG motor imagery classification based on multi-layer CNNs feature fusion","volume":"101","author":"Amin","year":"2019","journal-title":"Futur. Gener. Comput. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Waytowich, N., Lawhern, V.J., Garcia, J.O., Cummings, J., Faller, J., Sajda, P., and Vettel, J.M. (2018). Compact convolutional neural networks for classification of asynchronous steady-state visual evoked potentials. J. Neural Eng., 15.","DOI":"10.1088\/1741-2552\/aae5d8"},{"key":"ref_19","unstructured":"Coretto, G.A.P., Gareis, I., and Rufiner, H.L. (2017, January 1). Open access database of EEG signals recorded during imagined speech. Proceedings of the 12th International Symposium on Medical Information Processing and Analysis, Tandil, Argentina."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Garc\u00eda-Salinas, J.S., Villase\u00f1or-Pineda, L., Reyes-Garc\u00eda, C.A., and Torres-Garc\u00eda, A. (2018). Tensor decomposition for imagined speech discrimination in EEG. Advances in Computational Intelligence. MICAI 2018, Springer International Publishing.","DOI":"10.1007\/978-3-030-04497-8_20"},{"key":"ref_21","unstructured":"Cooney, C., Korik, A., Raffaella, F., and Coyle, D. (2019, January 16\u201320). Classification of imagined spoken word-pairs using convolutional neural networks. Proceedings of the 8th Graz Brain Computer Interface Conference 2019, Graz, Austria."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Tan, P., Sa, W., and Yu, L. (2016., January 19\u201322). Applying extreme learning machine to classification of EEG BCI. Proceedings of the 2016 IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems (CYBER), Chengdu, China.","DOI":"10.1109\/CYBER.2016.7574827"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"5391","DOI":"10.1002\/hbm.23730","article-title":"Deep learning with convolutional neural networks for EEG decoding and visualization","volume":"38","author":"Schirrmeister","year":"2017","journal-title":"Hum. Brain Mapp."},{"key":"ref_24","unstructured":"Ruder, S. (2016). An overview of gradient descent optimization algorithms. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Muhammad, Y., and Vaino, D. (2019). Controlling Electronic Devices with brain rhythms\/electrical activity using artificial neural network (ANN). Bioengineering, 6.","DOI":"10.3390\/bioengineering6020046"}],"container-title":["Computers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-431X\/9\/2\/46\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T09:34:36Z","timestamp":1760175276000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-431X\/9\/2\/46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,1]]},"references-count":25,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2020,6]]}},"alternative-id":["computers9020046"],"URL":"https:\/\/doi.org\/10.3390\/computers9020046","relation":{},"ISSN":["2073-431X"],"issn-type":[{"value":"2073-431X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,6,1]]}}}