Open AccessDEVELOPMENT OF THE NEURAL NETWORK FOR SOLVING THE PROBLEM OF SPEECH RECOGNITION
Author(s) -
M.D. Dilmagambetova,
Оrken Mamyrbayev
Publication year - 2021
Publication title -
izvestiâ nacionalʹnoj akademii nauk respubliki kazahstan. seriâ fiziko-matematičeskaâ/izvestiâ nacionalʹnoj akademii nauk respubliki kazahstan. seriâ fiziko-matematičeskaâ
Language(s) - English
Resource type - Journals
eISSN - 2518-1726
pISSN - 1991-346X
DOI - 10.32014/2021.2518-1726.3
Subject(s) - generalization , artificial neural network , computer science , time delay neural network , backpropagation , word error rate , artificial intelligence , generalization error , sequence (biology) , machine learning , speech recognition , mathematics , mathematical analysis , biology , genetics
The article discusses a method for solving the problem of speech recognition on the example of recognizing individual words of a limited dictionary using a forward propagation neural network trained by the error back propagation method. The goal was to create a neural network model for recognizing the solution of individual words, analyze the training characteristics and behavior of the constructed neural network. Based on the input data and output requirements, a feedback neural network selected. To train the selected neural network model, a back propagation algorithm was chosen. The developed neural network demonstrated the expected behavior associated with learning and generalization errors. It found that even if the generalization error decreases as the learning sequence increases, the errors begin to fluctuate regardless of the introduction of a dynamic learning rate. The network sufficiently trained to meet the generalization error requirements, but there is stillroom to improve the generalization error. Practical results of training the constructed neural network at different sizes of the training sample presented.