期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2019
卷号：97
期号：8
页码：2404-2415
出版社：Journal of Theoretical and Applied
摘要：Speech recognition has a high complexity and a broad range of applications, since it has to predict the word under many types of distortions. This paper aims to compare the performance of different optimization techniques like genetic algorithm, particle swarm optimization and artificial bee colony for optimizing the different hidden layers and neurons of the hidden layers of artificial neural network, for maximum speech recognition accuracy. The features of the input speech signals are extracted using amplitude modulation spectrogram. The outcome demonstrates that the accuracy of artificial bee colony is 95.3% and it performs better when compared with the other optimization techniques.
