CNN Architectures and Feature Extraction Methods for EEG Imaginary Speech Recognition
Speech is a complex mechanism allowing us to communicate our needs, desires and thoughts. In some cases of neural dysfunctions, this ability is highly affected, which makes everyday life activities that require communication a challenge. This paper studies different parameters of an intelligent imag...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-06-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/13/4679 |
_version_ | 1797433993390456832 |
---|---|
author | Ana-Luiza Rusnac Ovidiu Grigore |
author_facet | Ana-Luiza Rusnac Ovidiu Grigore |
author_sort | Ana-Luiza Rusnac |
collection | DOAJ |
description | Speech is a complex mechanism allowing us to communicate our needs, desires and thoughts. In some cases of neural dysfunctions, this ability is highly affected, which makes everyday life activities that require communication a challenge. This paper studies different parameters of an intelligent imaginary speech recognition system to obtain the best performance according to the developed method that can be applied to a low-cost system with limited resources. In developing the system, we used signals from the Kara One database containing recordings acquired for seven phonemes and four words. We used in the feature extraction stage a method based on covariance in the frequency domain that performed better compared to the other time-domain methods. Further, we observed the system performance when using different window lengths for the input signal (0.25 s, 0.5 s and 1 s) to highlight the importance of the short-term analysis of the signals for imaginary speech. The final goal being the development of a low-cost system, we studied several architectures of convolutional neural networks (CNN) and showed that a more complex architecture does not necessarily lead to better results. Our study was conducted on eight different subjects, and it is meant to be a subject’s shared system. The best performance reported in this paper is up to 37% accuracy for all 11 different phonemes and words when using cross-covariance computed over the signal spectrum of a 0.25 s window and a CNN containing two convolutional layers with 64 and 128 filters connected to a dense layer with 64 neurons. The final system qualifies as a low-cost system using limited resources for decision-making and having a running time of 1.8 ms tested on an AMD Ryzen 7 4800HS CPU. |
first_indexed | 2024-03-09T10:24:55Z |
format | Article |
id | doaj.art-1256c6516d764dfaaad5fd61a160e24a |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T10:24:55Z |
publishDate | 2022-06-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-1256c6516d764dfaaad5fd61a160e24a2023-12-01T21:41:13ZengMDPI AGSensors1424-82202022-06-012213467910.3390/s22134679CNN Architectures and Feature Extraction Methods for EEG Imaginary Speech RecognitionAna-Luiza Rusnac0Ovidiu Grigore1Department of Applied Electronics and Information Engineering, Faculty of Electronics, Telecommunications and Information Technology, Polytechnic University of Bucharest, 060042 Bucharest, RomaniaDepartment of Applied Electronics and Information Engineering, Faculty of Electronics, Telecommunications and Information Technology, Polytechnic University of Bucharest, 060042 Bucharest, RomaniaSpeech is a complex mechanism allowing us to communicate our needs, desires and thoughts. In some cases of neural dysfunctions, this ability is highly affected, which makes everyday life activities that require communication a challenge. This paper studies different parameters of an intelligent imaginary speech recognition system to obtain the best performance according to the developed method that can be applied to a low-cost system with limited resources. In developing the system, we used signals from the Kara One database containing recordings acquired for seven phonemes and four words. We used in the feature extraction stage a method based on covariance in the frequency domain that performed better compared to the other time-domain methods. Further, we observed the system performance when using different window lengths for the input signal (0.25 s, 0.5 s and 1 s) to highlight the importance of the short-term analysis of the signals for imaginary speech. The final goal being the development of a low-cost system, we studied several architectures of convolutional neural networks (CNN) and showed that a more complex architecture does not necessarily lead to better results. Our study was conducted on eight different subjects, and it is meant to be a subject’s shared system. The best performance reported in this paper is up to 37% accuracy for all 11 different phonemes and words when using cross-covariance computed over the signal spectrum of a 0.25 s window and a CNN containing two convolutional layers with 64 and 128 filters connected to a dense layer with 64 neurons. The final system qualifies as a low-cost system using limited resources for decision-making and having a running time of 1.8 ms tested on an AMD Ryzen 7 4800HS CPU.https://www.mdpi.com/1424-8220/22/13/4679imaginary speechconvolutional neural networkelectroencephalographysignal processingKara One database |
spellingShingle | Ana-Luiza Rusnac Ovidiu Grigore CNN Architectures and Feature Extraction Methods for EEG Imaginary Speech Recognition Sensors imaginary speech convolutional neural network electroencephalography signal processing Kara One database |
title | CNN Architectures and Feature Extraction Methods for EEG Imaginary Speech Recognition |
title_full | CNN Architectures and Feature Extraction Methods for EEG Imaginary Speech Recognition |
title_fullStr | CNN Architectures and Feature Extraction Methods for EEG Imaginary Speech Recognition |
title_full_unstemmed | CNN Architectures and Feature Extraction Methods for EEG Imaginary Speech Recognition |
title_short | CNN Architectures and Feature Extraction Methods for EEG Imaginary Speech Recognition |
title_sort | cnn architectures and feature extraction methods for eeg imaginary speech recognition |
topic | imaginary speech convolutional neural network electroencephalography signal processing Kara One database |
url | https://www.mdpi.com/1424-8220/22/13/4679 |
work_keys_str_mv | AT analuizarusnac cnnarchitecturesandfeatureextractionmethodsforeegimaginaryspeechrecognition AT ovidiugrigore cnnarchitecturesandfeatureextractionmethodsforeegimaginaryspeechrecognition |