Aquila-Eagle-Based Deep Convolutional Neural Network for Speech Recognition Using EEG Signals

Abstract

The conventional BCI system experiences several issues such as background noise interference, lower precision rate and high cost. Hence, a novel speech recognition model which is based on the optimized Deep-CNN is proposed in this research article so as to restrain the issues related to the conventional speech recognition method. The significance of the research relies on the proposed method algorithm known as Aquila-eagle optimization, which effectively tunes the parameters of Deep-CNN. The most significant features are extracted in the feature selection process, which enhance the precision of the speech recognition model. Further unwanted noises in the EEG signals are constructively removed in the pre-processing stage to boost the accuracy of the Deep-CNN classifier.From the experimental outcomes it is demonstrated that the proposed Aquila-eagle-based DeepCNN outperformed other state-of-the-art techniques in terms of accuracy, precision, and recall with the values of 93.11%, 90.89%, and 93.11%, respectively.