Can we identify the category of imagined phoneme from EEG?

Panachakel, Jerrin Thomas; Sharma, Kanishka; Anusha, A S; Ramakrishnan, A. G.

doi:10.1109/embc46164.2021.9630604

Cited by 7 publications

(4 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using open-source hardware and software, all 44 phonemes of the English language were correctly identified in the vast majority of intrasubject and intersubject classification cases at a maximum average accuracy of 98% with SVM. No prior work used a complete phoneme set for a language ( Panachakel et al, 2021 ). The maximum averaged F1 score was 0.55 ± 0.01 and an AUC-ROC of 0.68 ± 0.002 with KNN.…”

Section: Discussionmentioning

confidence: 99%

“…The breadth of disjointed linguistic components has also constrained BCIs. Some studies have focused on complete words, syllables, sentences, or phonemes ( Jahangiri and Sepulveda, 2019 ; Panachakel et al, 2021 ). Because every language comprises multiple phonemes, no imagined speech EEG study has examined all the constituent phonemes of a language.…”

Section: Introductionmentioning

confidence: 99%

“…Phonemes are the basic components of every spoken language, and English has 44 separate phonemes ( Ariki, 1991 ). Previous research has identified the EEG-based separability of phonemes ( Panachakel et al, 2021 ). The use of EEG corresponding to unique phonemes has been successfully reported in an imagined speech BCI ( Suyuncheva et al, 2020 ; Panachakel et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

“…Previous research has identified the EEG-based separability of phonemes ( Panachakel et al, 2021 ). The use of EEG corresponding to unique phonemes has been successfully reported in an imagined speech BCI ( Suyuncheva et al, 2020 ; Panachakel et al, 2021 ). However, no existing EEG BCIs have utilized all English-language phonemes.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Evaluation of an English language phoneme-based imagined speech brain computer interface with low-cost electroencephalography

LaRocco,

Tahmina,

Lecian

et al. 2023

Front. Neuroinform.

View full text Add to dashboard Cite

IntroductionParalyzed and physically impaired patients face communication difficulties, even when they are mentally coherent and aware. Electroencephalographic (EEG) brain–computer interfaces (BCIs) offer a potential communication method for these people without invasive surgery or physical device controls.MethodsAlthough virtual keyboard protocols are well documented in EEG BCI paradigms, these implementations are visually taxing and fatiguing. All English words combine 44 unique phonemes, each corresponding to a unique EEG pattern. In this study, a complete phoneme-based imagined speech EEG BCI was developed and tested on 16 subjects.ResultsUsing open-source hardware and software, machine learning models, such as k-nearest neighbor (KNN), reliably achieved a mean accuracy of 97 ± 0.001%, a mean F1 of 0.55 ± 0.01, and a mean AUC-ROC of 0.68 ± 0.002 in a modified one-versus-rest configuration, resulting in an information transfer rate of 304.15 bits per minute. In line with prior literature, the distinguishing feature between phonemes was the gamma power on channels F3 and F7.DiscussionHowever, adjustments to feature selection, trial window length, and classifier algorithms may improve performance. In summary, these are iterative changes to a viable method directly deployable in current, commercially available systems and software. The development of an intuitive phoneme-based EEG BCI with open-source hardware and software demonstrates the potential ease with which the technology could be deployed in real-world applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%