A State-of-the-Art Review of EEG-Based Imagined Speech Decoding.

Currently, the most used method to measure brain activity under a non-invasive procedure is the electroencephalogram (EEG). This is because of its high temporal resolution, ease of use, and safety. These signals can be used under a Brain Computer Interface (BCI) framework, which can be implemented to provide a new communication channel to people that are unable to speak due to motor disabilities or other neurological diseases. Nevertheless, EEG-based BCI systems have presented challenges to be implemented in real life situations for imagined speech recognition due to the difficulty to interpret EEG signals because of their low signal-to-noise ratio (SNR). As consequence, in order to help the researcher make a wise decision when approaching this problem, we offer a review article that sums the main findings of the most relevant studies on this subject since 2009. This review focuses mainly on the pre-processing, feature extraction, and classification techniques used by several authors, as well as the target vocabulary. Furthermore, we propose ideas that may be useful for future work in order to achieve a practical application of EEG-based BCI systems toward imagined speech decoding.

Recognition of EEG Signals from Imagined Vowels Using Deep Learning Methods.

The use of imagined speech with electroencephalographic (EEG) signals is a promising field of brain-computer interfaces (BCI) that seeks communication between areas of the cerebral cortex related to language and devices or machines. However, the complexity of this brain process makes the analysis and classification of this type of signals a relevant topic of research. The goals of this study were: to develop a new algorithm based on Deep Learning (DL), referred to as CNNeeg1-1, to recognize EEG signals in imagined vowel tasks; to create an imagined speech database with 50 subjects specialized in imagined vowels from the Spanish language (/a/,/e/,/i/,/o/,/u/); and to contrast the performance of the CNNeeg1-1 algorithm with the DL Shallow CNN and EEGNet benchmark algorithms using an open access database (BD1) and the newly developed database (BD2). In this study, a mixed variance analysis of variance was conducted to assess the intra-subject and inter-subject training of the proposed algorithms. The results show that for intra-subject training analysis, the best performance among the Shallow CNN, EEGNet, and CNNeeg1-1 methods in classifying imagined vowels (/a/,/e/,/i/,/o/,/u/) was exhibited by CNNeeg1-1, with an accuracy of 65.62% for BD1 database and 85.66% for BD2 database.

Análisis de señales electroencefalográficas para la clasificación de habla imaginada / Electroencephalographic Signals Analysis for Imagined Speech Classification

El presente trabajo tiene como objetivo interpretar las señales de EEG registradas durante la pronunciación imaginada de palabras de un vocabulario reducido, sin emitir sonidos ni articular movimientos (habla imaginada o no pronunciada) con la intención de controlar un dispositivo. Específicamente, el vocabulario permitiría controlar el cursor de la computadora, y consta de las palabras del lenguaje español: "arriba", "abajo", "izquierda", "derecha", y "seleccionar". Para ello, se registraron las señales de EEG de 27 individuos utilizando un protocolo básico para saber a priori en qué segmentos de la señal la persona imagina la pronunciación de la palabra indicada. Posteriormente, se utiliza la transformada wavelet discreta (DWT) para extraer características de los segmentos que son usados para calcular la energía relativa wavelet (RWE) en cada una de los niveles en los que la señal es descompuesta, y se selecciona un subconjunto de valores RWE provenientes de los rangos de frecuencia menores a 32 Hz. Enseguida, éstas se concatenan en dos configuraciones distintas: 14 canales (completa) y 4 canales (los más cercanos a las áreas de Broca y Wernicke). Para ambas configuraciones se entrenan tres clasificadores: Naive Bayes (NB), Random Forest (RF) y Máquina de vectores de soporte (SVM). Los mejores porcentajes de exactitud se obtuvieron con RF cuyos promedios fueron 60.11% y 47.93% usando las configuraciones de 14 canales y 4 canales, respectivamente. A pesar de que los resultados aún son preliminares, éstos están arriba del 20%, es decir, arriba del azar para cinco clases. Con lo que se puede conjeturar que las señales de EEG podrían contener información que hace posible la clasificación de las pronunciaciones imaginadas de las palabras del vocabulario reducido.

This work aims to interpret the EEG signals associated with actions to imagine the pronunciation of words that belong to a reduced vocabulary without moving the articulatory muscles and without uttering any audible sound (imagined or unspoken speech). Specifically, the vocabulary reflects movements to control the cursor on the computer, and consists of the Spanish language words: "arriba", "abajo", "izquierda", "derecha", and "seleccionar". To do this, we have recorded EEG signals from 27 subjects using a basic protocol to know a priori in what segments of the signal a subject imagines the pronunciation of the indicated word. Subsequently, discrete wavelet transform (DWT) is used to extract features from the segments. These are used to compute relative wavelet energy (RWE) in each of the levels in that EEG signal is decomposed and, it is selected a RWE values subset with the frequencies smaller than 32 Hz. Then, these are concatenated in two different configurations: 14 channels (full) and 4 channels (the channels nearest to the brain areas of Wernicke and Broca). The following three classifiers were trained using both configurations: Naive Bayes (NB), Random Forest (RF) and support vector machines (SVM). The best accuracies were obtained by RF whose averages were 60.11% and 47.93% using both configurations, respectively. Even though, the results are still preliminary, these are above 20%, this means they are more accurate than chance for five classes. Based on them, we can conjecture that the EEG signals could contain information needed for the classification of the imagined pronunciations of the words belonging to a reduced vocabulary.