A Spectrotemporal EEG Mapping Approach for Decoding Imagined Marathi Language Phonemes
Received: 22 January 2024 | Revised: 6 February 2024 and 9 February 2024 | Accepted: 11 February 2024 | Online: 2 April 2024
Corresponding author: Umesh Mhapankar
Abstract
Individuals facing verbal communication impairments resulting from brain disorders like paralysis or autism encounter significant challenges when unable to articulate speech. This research proposes the design and development of a wearable system capable of decoding imagined speech using electroencephalogram (EEG) signals obtained during the mental process of speech generation. The system’s main objective is to offer an alternative communication method for individuals who can hear and think but face challenges in articulating their thoughts verbally. The design suggested includes user-friendliness, wearability, and comfort for seamless integration into daily life. A minimal number of electrodes are strategically placed on the scalp to minimize invasiveness. Achieving precise localization of the cortical areas responsible for generating the EEG patterns during imagined speech is vital for accurate decoding. Literature studies are utilized to determine the cortical positions associated with speech processing. Due to the inherent limitations in EEG spatial resolution, meticulous experiments are conducted to map the scalp positions onto their corresponding cortical counterparts. Specifically, we focus on identifying the scalp location over the superior temporal gyrus (T3) using the internationally recognized 10-20 electrode placement system by employing a circular periphery movement with a 2 cm distance increment. Our research involves nine subjects spanning various age groups, with the youngest being 23 and the oldest 65. Each participant undergoes ten iterations, during which they imagine six Marathi syllables. Our work contributes to the development of wearable assistive technology, enabling mute individuals to communicate effectively by translating their imagined speech into actionable commands. This innovation ultimately enhances their social participation and overall well-being.
Keywords:
EEG, imagined speech, location mapping, Wernicke areaDownloads
References
S. Martin, C. Mikutta, R. T. Knight, and B. N. Pasley, "Understanding and Decoding Thoughts in the Human Brain," Frontiers for Young Minds. https://kids.frontiersin.org/articles/10.3389/frym.2016.00004.
S. Martin et al., "Decoding spectrotemporal features of overt and covert speech from the human cortex," Frontiers in Neuroengineering, vol. 7, May 2014.
P. L. Nunez and R. Srinivasan, Electric Fields of the Brain: The Neurophysics of EEG, 2nd ed. Oxford, UK: Oxford University Press, 2005.
R. E. Weller, "Chapter 27: Two cortical visual systems in Old World and New World primates," in Progress in Brain Research, vol. 75, T. P. Hicks and G. Benedek, Eds. Elsevier, 1988, pp. 293–306.
J. T. Panachakel and A. G. Ramakrishnan, "Decoding Covert Speech From EEG-A Comprehensive Review," Frontiers in Neuroscience, vol. 15, Apr. 2021, Art. no. 642251.
S. R. Synigal, E. S. Teoh, and E. C. Lalor, "Including Measures of High Gamma Power Can Improve the Decoding of Natural Speech From EEG," Frontiers in Human Neuroscience, vol. 14, 2020, Art. no. 130¸https://doi.org/10.3389/fnhum.2020.00130.
U. Mhapankar and M. M. Shah, "Mapping the Imagined Speech Location on the Brain Scalp Through Magnetoencephalography (MEG)," International Journal of Recent Technology and Engineering (IJRTE), vol. 11, Jul. 2022.
U. Mhapankar and M. M. Shah, "Mapping the Imagined Speech Location on the Brain Scalp Through Magnetoencephalography (MEG)," International Journal of Recent Technology and Engineering (IJRTE), vol. 11, Jul. 2022.
S. Deng, R. Srinivasan, and M. D’Zmura, "Cortical Signatures of Heard and Imagined Speech Envelopes," Aug. 2013, [Online]. Available: https://cnslab.ss.uci.edu/speechattention/content/DengSrinivasanDZmura2013.pdf.
J. Derix, O. Iljina, J. Weiske, A. Schulze-Bonhage, A. Aertsen, and T. Ball, "From speech to thought: the neuronal basis of cognitive units in non-experimental, real-life communication investigated using ECoG," Frontiers in Human Neuroscience, vol. 8, Jun. 2014.
H. Lu, J. Li, L. Zhang, S. S. M. Chan, L. C. W. Lam, and for the Open Access Series of Imaging Studies, "Dynamic changes of region-specific cortical features and scalp-to-cortex distance: implications for transcranial current stimulation modeling," Journal of NeuroEngineering and Rehabilitation, vol. 18, no. 1, Jan. 2021, Art. no. 2.
B. Oshri, N. Khandwala, and M. Chopra, "Classifying Syllables in Imagined Speech using EEG Data," [Online]. Available: https://cs229.stanford.edu/proj2014/Barak%20Oshri,%20Nishith%20Khandwala,%20Manu%20Chopra,%20Classifying%20Syllables%20in%20Imagined%20Speech%20using%20EEG%20Data.pdf.
A. Borna et al., "A 20-channel magnetoencephalography system based on optically pumped magnetometers," Physics in Medicine and Biology, vol. 62, no. 23, pp. 8909–8923, Nov. 2017.
C. Im and J.-M. Seo, "A review of electrodes for the electrical brain signal recording," Biomedical Engineering Letters, vol. 6, no. 3, pp. 104–112, Aug. 2016.
D. A. Rojas, L. A. Góngora, and O. L. Ramos, "EEGSignal Analysis Related to Speech Process through Bci Device Emotiv, FFT and Statistical Methods," ARPN Journal of Engineering and Applied Sciences, vol. 11, no. 5, pp. 3074–3080, 2016.
D. W. Jeong, G. H. Kim, N. Y. Kim, Z. Lee, S. D. Jung, and J.-O. Lee, "A high-performance transparent graphene/vertically aligned carbon nanotube (VACNT) hybrid electrode for neural interfacing," RSC Advances, vol. 7, no. 6, pp. 3273–3281, Jan. 2017.
"Marathi phonology," Wikipedia. Feb. 20, 2024, [Online]. Available: https://en.wikipedia.org/w/index.php?title=Marathi_phonology&oldid=1209133005.
U. Mhapankar and M. Shah, "The Comparison of the Dry Electrodes to wet Ag/AgCI electrode for Decoding Imagined Speech from the EEG," in 2022 International Conference for Advancement in Technology (ICONAT), Goa, India, Jan. 2022, pp. 1–6.
M. B. Ayed, "Balanced Communication-Avoiding Support Vector Machine when Detecting Epilepsy based on EEG Signals," Engineering, Technology & Applied Science Research, vol. 10, no. 6, pp. 6462–6468, Dec. 2020.
G. Anuradha and D. N. Jamal, "Classification of Dementia in EEG with a Two-Layered Feed Forward Artificial Neural Network," Engineering, Technology & Applied Science Research, vol. 11, no. 3, pp. 7135–7139, Jun. 2021.
M. A. Alsuwaiket, "Feature Extraction of EEG Signals for Seizure Detection Using Machine Learning Algorthims," Engineering, Technology & Applied Science Research, vol. 12, no. 5, pp. 9247–9251, Oct. 2022.
Downloads
How to Cite
License
Copyright (c) 2024 Umesh Mhapankar, Milind Shah
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
