Optimization of MLP Using Genetic Algorithms Applied to Arabic Speech Recognition

Abstract

This paper presents a novel system for Arabic speech recognition of Arabic isolated words with mono-locutor and a small vocabulary. We have used a database consisting of eleven isolated Arabic words each of them was repeated twenty five times by the same -locutor. Mel Frequency Cepstral Coefficient (MFCC) and Bionic Wavelet Transform (BWT) are used for feature extraction from each recorded word. The obtained coefficients were then concatenated to construct one input node of a Multi-Layer Perceptual (MLP) used for features classification and recognition. We describe in this paper the use of Genetic Algorithm (GA) for optimizing the topology of each Multi-Layer Perceptron (MLP). So, the GA is utilized to find the optimal number of neurons in input layer and in hidden layer, the training epochs and the learning goal of network. From the results, it was observed that the integration of the GA with feed forward network can improve classification rate to 100%