Systematic Review of EEG-Based Imagined Speech Classification Methods

Abstract

This systematic review examines EEG-based imagined speech classification, emphasizing directional words essential for development in the brain-computer interface (BCI). This study employed a structured methodology to analyze approaches using public datasets, ensuring systematic evaluation and validation of results. This review highlights the feature extraction techniques that are pivotal to classification performance. These include deep learning, adaptive optimization, and frequency-specific decomposition, which enhance accuracy and robustness. Classification methods were explored by comparing traditional machine learning with deep learning and emphasizing the role of brain lateralization in imagined speech for effective recognition and classification. This study discusses the challenges of generalizability and scalability in imagined speech recognition, focusing on subject-independent approaches and multiclass scalability. Performance benchmarking across various datasets and methodologies revealed varied classification accuracies, reflecting the complexity and variability of EEG signals. This review concludes that challenges remain despite progress, particularly in classifying directional words. Future research directions include improved signal processing techniques, advanced neural network architectures, and more personalized, adaptive BCI systems. This review is critical for future efforts to develop practical communication tools for individuals with speech and motor impairments using EEG-based BCIs.

Keywords: BCI; EEG; brain–computer interfaces; electroencephalogram; imagined speech; inner speech.

Figure 1

Study selection process.

Figure 2

Accuracy plot across all papers using the datasets Nieto et al. (2022) [29] and Coretto et al. (2017) [28]. The results are derived from the following studies: Berg et al. (2021) [25], Biswas et al. (2018) [27], Biswas et al. (2022) [21], Cooney et al. (2020) [24], Dash et al. (2022) [16], García-Salinas et al. (2018) [22], Gasparini et al. (2022) [26], Kamble et al. (2022) [19], Kamble et al. (2023) [20], Lee et al. (2020) [17], Lee et al. (2021) [18] and Merola et al. (2023) [23].

Figure 3

Boxplot illustrating accuracies based on subject dependency across studies using the datasets Nieto et al. (2022) [29] and Coretto et al. (2017) [28]. The data are derived from the following studies: Berg et al. (2021) [25], Biswas et al. (2018) [27], Biswas et al. (2022) [21], Cooney et al. (2020) [24], Dash et al. (2022) [16], García-Salinas et al. (2018) [22], Gasparini et al. (2022) [26], Kamble et al. (2022) [19], Kamble et al. (2023) [20], Lee et al. (2020) [17], Lee et al. (2021) [18] and Merola et al. (2023) [23].