Integrating Neuro-genetic Connection Weights Strategy for Spoken Malay Speech Recognition Model

Abstract

This paper proposed weights connection strategy to improve the recognition performance for spoken Malay speech recognition. The strategy is used to combine genetic algorithms (GA) and neural network (NN) methods. Both algorithms are the separate modules and were used to find the optimum weights for the hidden and output layers of feed-forward artificial neural network (ANN) model. There are two different GA techniques used in this research, one is standard GA and slightly different technique from standard GA also has been proposed. Thus, from the results, it was observed that the performance of proposed GA algorithm while combined with NN shows better result than standard GA and NN models alone. Integrating the GA with feed-forward network can improve mean square error (MSE) performance and with good connection strategy by this two stage training scheme, the recognition rate can be increased up to 90%.