Imagined Speech Research Articles

Towards imagined speech: Identification of brain states from EEG signals for BCI-based communication systems

BackgroundThe electroencephalogram (EEG) based brain-computer interface (BCI) system employing imagined speech serves as a mechanism for decoding EEG signals to facilitate control over external devices or communication with the external world at the moment the user desires. To effectively deploy such BCIs, it is imperative to accurately discern various brain states from continuous EEG signals when users initiate word imagination. New methodThis study involved the acquisition of EEG signals from 15 subjects engaged in four states: resting, listening, imagined speech, and actual speech, each involving a predefined set of 10 words. The EEG signals underwent preprocessing, segmentation, spatio-temporal and spectral analysis of each state, and functional connectivity analysis using the phase locking value (PLV) method. Subsequently, five features were extracted from the frequency and time-frequency domains. Classification tasks were performed using four machine learning algorithms in both pair-wise and multiclass scenarios, considering subject-dependent and subject-independent data. ResultsIn the subject-dependent scenario, the random forest (RF) classifier achieved a maximum accuracy of 94.60 % for pairwise classification, while the artificial neural network (ANN) classifier achieved a maximum accuracy of 66.92 % for multiclass classification. In the subject-independent scenario, the random forest (RF) classifier achieved maximum accuracies of 81.02 % for pairwise classification and 55.58 % for multiclass classification. Moreover, EEG signals were classified based on frequency bands and brain lobes, revealing that the theta (θ) and delta (δ) bands, as well as the frontal and temporal lobes, are sufficient for distinguishing between brain states. ConclusionThe findings promise to develop a system capable of automatically segmenting imagined speech segments from continuous EEG signals.

Feasibility of decoding covert speech in ECoG with a Transformer trained on overt speech

Several attempts for speech brain–computer interfacing (BCI) have been made to decode phonemes, sub-words, words, or sentences using invasive measurements, such as the electrocorticogram (ECoG), during auditory speech perception, overt speech, or imagined (covert) speech. Decoding sentences from covert speech is a challenging task. Sixteen epilepsy patients with intracranially implanted electrodes participated in this study, and ECoGs were recorded during overt speech and covert speech of eight Japanese sentences, each consisting of three tokens. In particular, Transformer neural network model was applied to decode text sentences from covert speech, which was trained using ECoGs obtained during overt speech. We first examined the proposed Transformer model using the same task for training and testing, and then evaluated the model’s performance when trained with overt task for decoding covert speech. The Transformer model trained on covert speech achieved an average token error rate (TER) of 46.6% for decoding covert speech, whereas the model trained on overt speech achieved a TER of 46.3% (p>0.05;d=0.07)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$( p > 0.05; d=0.07)$$\\end{document}. Therefore, the challenge of collecting training data for covert speech can be addressed using overt speech. The performance of covert speech can improve by employing several overt speeches.

Decoding imagined speech with delay differential analysis.

Speech decoding from non-invasive EEG signals can achieve relatively high accuracy (70-80%) for strictly delimited classification tasks, but for more complex tasks non-invasive speech decoding typically yields a 20-50% classification accuracy. However, decoder generalization, or how well algorithms perform objectively across datasets, is complicated by the small size and heterogeneity of existing EEG datasets. Furthermore, the limited availability of open access code hampers a comparison between methods. This study explores the application of a novel non-linear method for signal processing, delay differential analysis (DDA), to speech decoding. We provide a systematic evaluation of its performance on two public imagined speech decoding datasets relative to all publicly available deep learning methods. The results support DDA as a compelling alternative or complementary approach to deep learning methods for speech decoding. DDA is a fast and efficient time-domain open-source method that fits data using only few strong features and does not require extensive preprocessing.

Imagined speech classification exploiting EEG power spectrum features.

Imagined speech recognition has developed as a significant topic of research in the field of brain-computer interfaces. This innovative technique has great promise as a communication tool, providing essential help to those with impairments. An imagined speech recognition model is proposed in this paper to identify the ten most frequently used English alphabets (e.g., A, D, E, H, I, N, O, R, S, T) and numerals (e.g., 0 to 9). A novel electroencephalogram (EEG) dataset was created by measuring the brain activity of 30 people while they imagined these alphabets and digits. As part of signal preprocessing, EEG signals are filtered before extracting delta, theta, alpha, and beta band power features. These features are used as input for classification using support vector machines, k-nearest neighbors, and random forest (RF) classifiers. It is identified that the RF classifier outperformed the others in terms of classification accuracy. Classification accuracies of 99.38% and 95.39% were achieved at the coarse-level and fine-level, respectively with the RF classifier. From our study, it is also revealed that the beta frequency band and the frontal lobe of the brain played crucial roles in imagined speech recognition. Furthermore, a comparative analysis against state-of-the-art techniques is conducted to demonstrate the efficacy of our proposed model.

Adaptive LDA Classifier Enhances Real-Time Control of an EEG Brain-Computer Interface for Decoding Imagined Syllables.

Brain-Computer Interfaces (BCIs) aim to establish a pathway between the brain and an external device without the involvement of the motor system, relying exclusively on neural signals. Such systems have the potential to provide a means of communication for patients who have lost the ability to speak due to a neurological disorder. Traditional methodologies for decoding imagined speech directly from brain signals often deploy static classifiers, that is, decoders that are computed once at the beginning of the experiment and remain unchanged throughout the BCI use. However, this approach might be inadequate to effectively handle the non-stationary nature of electroencephalography (EEG) signals and the learning that accompanies BCI use, as parameters are expected to change, and all the more in a real-time setting. To address this limitation, we developed an adaptive classifier that updates its parameters based on the incoming data in real time. We first identified optimal parameters (the update coefficient, UC) to be used in an adaptive Linear Discriminant Analysis (LDA) classifier, using a previously recorded EEG dataset, acquired while healthy participants controlled a binary BCI based on imagined syllable decoding. We subsequently tested the effectiveness of this optimization in a real-time BCI control setting. Twenty healthy participants performed two BCI control sessions based on the imagery of two syllables, using a static LDA and an adaptive LDA classifier, in randomized order. As hypothesized, the adaptive classifier led to better performances than the static one in this real-time BCI control task. Furthermore, the optimal parameters for the adaptive classifier were closely aligned in both datasets, acquired using the same syllable imagery task. These findings highlight the effectiveness and reliability of adaptive LDA classifiers for real-time imagined speech decoding. Such an improvement can shorten the training time and favor the development of multi-class BCIs, representing a clear interest for non-invasive systems notably characterized by low decoding accuracies.

Ensemble-based feature engineering mechanism to decode imagined speech from brain signals

Speech impairments, resulting from brain injuries, mental disorders, or vocal abuse, substantially affect an individual’s quality of life and can lead to social isolation. Brain–Computer Interfaces (BCIs), particularly those based on EEG, offer a promising support mechanism by harnessing brain signals. Owing to their clinical efficacy, cost-effective EEG devices, and expanding applications in the medical and social spheres, their usage has surged. This study introduces an ensemble-based feature engineering mechanism to pinpoint the optimal brain rhythm, channel subset, and feature set for accurately predicting imagined words from EEG signals via machine learning models. Leveraging the 2020 International BCI competition dataset, we employed bandpass filtering, channel wrapping, and ranking methods were applied to discern suitable brain rhythms and features associated with imagined speech. Subsequent application of kernel-based principal component analysis enabled us to compress the feature space dimensionality. We then trained various machine learning models, among which the kNN model excelled, achieving an average accuracy of 73% in a 10-fold cross-validation scheme ,surpassing 18% higher than the existing literature. The Gamma rhythm was identified as the most predictive of imagined speech from EEG brain signals. These advancements herald a new era of more precise and effective BCIs, poised to significantly improve the lives of those with speech impairments.

Optimized CNN‐Bi‐LSTM–Based BCI System for Imagined Speech Recognition Using FOA‐DWT

Speech imagery is emerging as a significant neuro‐paradigm for designing an electroencephalography (EEG)‐based brain–computer interface (BCI) system for the purpose of rehabilitation, medical neurology, and to aid people with disabilities in interacting with their surroundings. Neural correlates of speech imagery EEG signals are variable and weak as compared to the vocal state; hence, it is challenging to interpret them using machine learning (ML)–based classifiers. The applicability of modern deep learning methods such as convolutional neural networks (CNNs) and bidirectional long short‐term memory (Bi‐LSTM) networks has seen substantial advances in complex EEG signal analysis as compared to ML‐based methods. The objective of this article is to design a firefly‐optimized discrete wavelet transform (DWT) and CNN‐Bi‐LSTM–based imagined speech recognition (ISR) system to interpret imagined speech EEG signals. This study utilizes two publicly available datasets. EEG signal is enhanced using firefly optimization algorithm (FOA)–based optimized soft thresholding of high‐frequency detail components obtained by DWT decomposition. The enhanced EEG signal is augmented using sliding window data augmentation to increase the training data. Frequency‐domain features like power spectral density (PSD), frequency band power (FBP), band ratios, peak frequency, mean frequency, median frequency, spectral entropy, and relative power are extracted from augmented EEG segments. The extracted feature vector is fed to the designed CNN‐Bi‐LSTM classifier such that the EEG data are classified into two‐class, three‐class, and four‐class categories. To achieve optimal performance, the CNN‐Bi‐LSTM model was optimized using the Keras tuner library. The designed CNN consists of one‐dimensional (1‐D) convolutional layers and max pooling layers for familiarizing local associations along with mining hierarchical connections, and the Bi‐LSTM network acquires long‐term dependencies from the features learned by the former CNN. Bi‐LSTM network improves the performance and acquires potentially more affluent representations by looking at the sequence in both forward and reverse ways to capture representations that might be left unexploited by the sequential‐order kind alone. The performance of the designed FOA‐DWT‐CNN‐Bi‐LSTM–based ISR system is assessed using four evaluation measures: accuracy, F1 score, recall, and precision. It is found that the proposed system achieves the highest classification accuracy of 99.43 ± 2.5%, 94.41 ± 3.31%, and 89.57 ± 4.3% for two‐class, three‐class, and four‐class categories, respectively.

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

Paralyzed 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. Although 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. Using 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. However, 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.

Decoding of imagined speech electroencephalography neural signals using transfer learning method

The use of brain-computer interfaces to produce imagined speech from brain waves has the potential to assist individuals with difficulty producing speech or communicating silently. The decoding of covert speech has been observed to have limited efficacy due to the diverse nature of the associated measured brain waves and the limited number of covert speech databases. As a result, traditional machine learning algorithms for learning and inference are challenging, and one of the real alternatives could be to leverage transfer of learning. The main goals of this research were to create a new deep learning (DL) framework for decoding imagined speech electroencephalography (EEG) signals tasks using transfer learning and to transfer the model learning of the source task of an imagined speech EEG dataset to the model training on the target task of another imagined speech EEG dataset, essentially the cross-task learning transfer of discriminative characteristics of the source task to the target task of imagined speech. The experiment was carried out using two distinct open-access EEG datasets, FEIS and KaraOne, that recorded the imagined speech classes of neural signals from multiple individuals. The target FEIS model and the target KaraOne model for multiclass classification exhibit overall accuracy of 89.01% and 82.35%, respectively, according to the proposed transfer learning. The experiment results indicate that the cross-task deep transfer learning design reliably classifies the imagined speech EEG signals by applying the source task learning to the target task learning. The findings suggest the feasibility of a consistent strategy for classifying multiclass imagined speech with transfer learning, which could thereby open up the possibility of future investigation into cross-task imagined speech classification knowledge usability for generalization of new imagined speech prompts.

A BCI system for imagined Bengali speech recognition

Non-invasive brain-computer interface (BCI) can be used in imagined speech recognition to aid people with speech disorders and has been investigated in different languages. However, this technology is in a very early stage for Bengali speech recognition. Therefore, the aim of this research is to develop a BCI system that can recognize imagined Bengali speech. In this study, a non-invasive 14-channel electroencephalography (EEG) headset was employed to record the EEG signals from 30 subjects. The subjects were instructed to imagine 11 Bengali vowels ▪ and 10 digits ▪. Then, we extracted four statistical features from the recorded EEG signals. A coarse-to-fine level classification was performed to categorize the imagined EEG data by exploiting these features. The data was classified at coarse level to distinguish between a vowel and a digit. Each vowel and digit were then classified at the fine level. In our classification, random forest achieved the highest recognition accuracy of 84.28% at the coarse level and 76.13% at the fine level. In order to comprehend the role played by each brain lobe in recognizing imagined speech, we additionally examined each of the brain lobes. The frontal lobe demonstrated the highest accuracy, with a coarse level accuracy of 80.65% and a fine level accuracy of 66.31%. Moreover, the proposed model outperformed the reported literature in this field.

Towards Voice Reconstruction from EEG during Imagined Speech

Translating imagined speech from human brain activity into voice is a challenging and absorbing research issue that can provide new means of human communication via brain signals. Efforts to reconstruct speech from brain activity have shown their potential using invasive measures of spoken speech data, but have faced challenges in reconstructing imagined speech. In this paper, we propose NeuroTalk, which converts non-invasive brain signals of imagined speech into the user's own voice. Our model was trained with spoken speech EEG which was generalized to adapt to the domain of imagined speech, thus allowing natural correspondence between the imagined speech and the voice as a ground truth. In our framework, an automatic speech recognition decoder contributed to decomposing the phonemes of the generated speech, demonstrating the potential of voice reconstruction from unseen words. Our results imply the potential of speech synthesis from human EEG signals, not only from spoken speech but also from the brain signals of imagined speech.

Source Localization and Spectrum Analyzing of EEG in Stuttering State upon Dysfluent Utterances.

Purpose: The present study which addressed adults who stutter (AWS) attempted to investigate power spectral dynamics in the stuttering state by answering the questions using quantitative electroencephalography (qEEG). Method: A 64-channel electroencephalography (EEG) setup was used for data acquisition at 20 AWS. Since the speech, especially stuttering, causes significant noise in the EEG, 2 conditions of speech preparation (SP) and imagined speech (IS) were considered. EEG signals were decomposed into 6 bands. The corresponding sources were localized using the standard low-resolution electromagnetic tomography (sLORETA) tool in both fluent and dysfluent states. Results: Significant differences were noted after analyzing the time-locked EEG signals in fluent and dysfluent utterances. Consistent with previous studies, poor alpha and beta suppression in SP and IS conditions were localized in the left frontotemporal areas in a dysfluent state. This was partly true for the right frontal regions. In the theta range, disfluency was concurrence with increased activation in the left and right motor areas. Increased delta power in the left and right motor areas as well as increased beta2 power over left parietal regions was notable EEG features upon fluent speech. Conclusion: Based on the present findings and those of earlier studies, explaining the neural circuitries involved in stuttering probably requires an examination of the entire frequency spectrum involved in speech.

Optimized Rational Dilation Wavelet Transform for Automatic Imagined Speech Recognition

Imagined speech is a process in which a person imagines words without saying them. Electroencephalogram (EEG)-based brain-computer interfaces (BCI) systems help in automatically identifying imagined speech to facilitate persons with severe brain disorders. Extracting meaningful information from the raw EEG signal is a challenging task due to the nonstationary nature of EEG signals. Decomposing a signal into several sub-bands (SB) using rational dilation wavelet transform (RADWT) requires selecting predefined factual parameters, which is an arduous task. The main objective of this study is to propose an adaptive RADWT method capable of decomposing EEG signals by adaptively selecting the tuning parameters and classifying the EEG signals into distinct categories. The optimum tuning parameters of RADWT are obtained using particle swarm optimization and used to decompose the EEG signals into several SBs. Several statistical features are elicited from each SB and used to input six different machine learning algorithms. This work employs a 64-channel EEG dataset recorded from 15 healthy people for three categories: long words, short words, and vowels. The performance of the proposed AISR system is evaluated using seven performance evaluation metrics: accuracy, recall, precision, Cohen’s kappa, F1-score, and area-under-the-curve. The proposed system achieved the average classification accuracies of 87.26±1.12%, 89.23±0.95%, 95.5±0.68%, and 92.16±0.83% for long words, short-long words, short words, and vowels, respectively. When compared to the existing state-of-the-art, the proposed non-parametric decomposition approach and the Bagging algorithm achieved a 3%-5% improvement. The performance of the proposed method is validated using an open-access dataset.

Deep-Learning-Based BCI for Automatic Imagined Speech Recognition Using SPWVD

The electroencephalogram (EEG)-based brain–computer interface (BCI) has potential applications in neuroscience and rehabilitation. It benefits a person with neurological impairment to communicate their thoughts to the external world without using any appendages. Decoding imagined speech had limited success, mainly because neural signals are weak and more variable than overt speech, hence challenging to decode by machine-learning (ML)-based algorithms. In recent years, deep learning (DL) with convolutional neural networks (CNNs) has transformed computer vision and can perform pattern recognition better than the traditional ML-based algorithms. The objective of this article is to design a smoothed pseudo-Wigner–Ville distribution (SPWVD) and CNN-based automatic imagined speech recognition (AISR) system to recognize imagined words. This article uses a publically available 64-channel EEG dataset, collected from 15 healthy subjects for three categories: long words, short words, and vowels. The EEG signals were transformed into time–frequency representation (TFR) using SPWVD, which are used as an input to CNN such that the EEG dataset was identified and classified into binary and multiclass categories. In addition, the CNN model was optimized using a recently developed Keras-tuner library to achieve optimal performance. The performance of the SPWVD-CNN-driven AISR system is evaluated using seven performance evaluation metrics: accuracy (ACC), recall (REC), precision (PREC), Mathew’s correlation coefficient (MCC), Cohen’s kappa ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\kappa $ </tex-math></inline-formula> ), F1-score, and area under the curve (AUC). It is found that the proposed system achieved the maximum classification ACCs of 94.82%, 94.26%, 94.68%, and 84.50% for long words, short–long words, short words, and vowels, respectively. The proposed AISR strengthens the possibility of using imagined speech recognition as a future BCI application.

Neural decoding of imagined speech from EEG signals using the fusion of graph signal processing and graph learning techniques

Imagined Speech (IS) is the imagination of speech without using the tongue or muscles. In recent studies, IS tasks are increasingly investigated for the Brain-Computer Interface (BCI) applications. Electroencephalography (EEG) signals, which record brain activity, can be used to analyze BCI-based tasks utilizing Machine Learning (ML) methods. The current paper considers decoding IS brain waves using the fusion of classical signal processing, Graph Signal Processing (GSP), and Graph Learning (GL) based features. The proposed fusion method, named GraphIS (short for a Graph-based Imagined Speech BCI decoder), is applied to the four-class classification (three classes of the imagined words, in addition to the rest state) on EEG recordings of fifteen subjects. Results show that GSP and GL-based features can highly improve the performance of classification outcomes compared to using only classical signal processing features and over the state-of-the-art Common Spatial Pattern (CSP) feature extractor by considering the spatial information of the signals as well as interactions between channels in regions of interest. The proposed GraphIS method leads to a mean accuracy of 50.10% in the studied four-class IS classification task, compared to using only one feature set with an accuracy of 47.86% and 46.10%, and also the state-of-the-art CSP with an accuracy of 47.10%. Additionally, using an EEG connectivity map of the electrode signals obtained from GL methods, we also found a strong connection in the right frontal region as well as in the left frontal regions during IS, which had not been focused on in the previous IS papers.

Brain Computer Interfaces and Communication Disabilities: Ethical, Legal, and Social Aspects of Decoding Speech From the Brain.

A brain-computer interface technology that can decode the neural signals associated with attempted but unarticulated speech could offer a future efficient means of communication for people with severe motor impairments. Recent demonstrations have validated this approach. Here we assume that it will be possible in future to decode imagined (i.e., attempted but unarticulated) speech in people with severe motor impairments, and we consider the characteristics that could maximize the social utility of a BCI for communication. As a social interaction, communication involves the needs and goals of both speaker and listener, particularly in contexts that have significant potential consequences. We explore three high-consequence legal situations in which neurally-decoded speech could have implications: Testimony, where decoded speech is used as evidence; Consent and Capacity, where it may be used as a means of agency and participation such as consent to medical treatment; and Harm, where such communications may be networked or may cause harm to others. We then illustrate how design choices might impact the social and legal acceptability of these technologies.

EEG-Based Multiword Imagined Speech Classification for Persian Words.

This study focuses on providing a simple, extensible, and multiclass classifier for imagined words using EEG signals. Six Persian words, along with the silence (or idle state), were selected as input classes. The words can be used to control a mouse/robot movement or fill a simple computer form. The data set of this study was 10 recordings of five participants collected in five sessions. Each record had 20 repetitions of all words and the silence. Feature sets consist of normalized, 1 Hz resolution frequency spectrum of 19 EEG channels in 1 to 32 Hz bands. Majority rule on a bank of binary SVM classifiers was used to determine the corresponding class of a feature set. Mean accuracy and confusion matrix of the classifiers were estimated by Monte-Carlo cross-validation. According to recording the time difference of inter- and intraclass samples, three classification modes were defined. In the long-time mode, where all instances of a word in the whole database are involved, average accuracies were about 58% for Word-Silence, 60% for Word-Word, 40% for Word-Word-Silence, and 32% for the seven-class classification (6 Words+Silence). For the short-time mode, when only instances of the same record are used, the accuracies were 96, 75, 79, and 55%, respectively. Finally, in the mixed-time classification, where samples of every class are taken from a different record, the highest performance achieved with average accuracies was about 97, 97, 92, and 62%. These results, even in the worst case of the long-time mode, are meaningfully better than random and are comparable with the best reported results of previously conducted studies in this area.

EEG-Based Silent Speech Interface and its Challenges: A Survey

People with speech disorders could have social and welfare difficulties. Therefore, the silent speech interface (SSI) is needed to help them communicate. This interface decodes the speech from a human’s biosignal. The brain signals contain information from speech production to cover people with numerous speech disorders. Brain signals can be acquired non-invasively by electroencephalograph (EEG) and later transformed into the features for the input of speech pattern recognition. This review discusses the advancement of EEG-based SSI research and its current challenges. It mainly discussed the acquisition protocol, spectral-spatial-temporal characterization of EEG-based imagined speech, classification techniques with leave-one-subject or session-out cross-validation, and related real-world environmental issues. It aims to aid future imagined speech decoding research in exploring the proper methods to overcome the problems.

The Effects of Classification Method and Electrode Configuration on EEG-based Silent Speech Classification.

The effective classification for imagined speech and intended speech is of great help to the development of speech-based brain-computer interfaces (BCIs). This work distinguished imagined speech and intended speech by employing the cortical EEG signals recorded from scalp. EEG signals from eleven subjects were recorded when they produced Mandarin-Chinese monosyllables in imagined speech and intended speech, and EEG features were classified by the common spatial pattern, time-domain, frequency-domain and Riemannian manifold based methods. The classification results indicated that the Riemannian manifold based method yielded the highest classification accuracy of 85.9% among the four classification methods. Moreover, the classification accuracy with the left-only brain electrode configuration was close to that with the whole brain electrode configuration. The findings of this work have potential to extend the output commands of silent speech interfaces.

Decoding Imagined Speech and Computer Control using Brain Waves

BackgroundIn this work, we explore the possibility of decoding Imagined Speech (IS) brain waves using machine learning techniques. ApproachWe design two finite state machines to create an interface for controlling a computer system using an IS-based brain–computer interface. To decode IS signals, we propose a covariance matrix of Electroencephalogram channels as input features, covariance matrices projection to tangent space for obtaining vectors from matrices, principal component analysis for dimension reduction of vectors, an artificial neural network (ANN) as a classification model, and bootstrap aggregation for creating an ensemble of ANN models. ResultBased on these findings, we are first to use an IS-based system to operate a computer and obtain an information transfer rate of 21-bits-per-minute. The proposed approach can decode the IS signal with a mean classification accuracy of 85% on classifying one long vs. short word. Our proposed approach can also differentiate between IS and rest state brain signals with a mean classification accuracy of 94%. ComparisonAfter comparison, we show that our approach performs equivalent to the state-of-the-art approach (SOTA) on decoding long vs. short word classification task. We also show that the proposed method outperforms SOTA significantly on decoding three short words and vowels with an average margin of 11% and 9%, respectively. ConclusionThese results show that the proposed approach can decode a wide variety of IS signals and is practically applicable in a real-time environment.