Signal Processing and Information Technology. Second International Joint Conference, SPIT 2012, Dubai, UAE, September 20-21, 2012, Revised Selected Papers

Research Article

Dynamic Neuro-genetic Weights Connection Strategy for Isolated Spoken Malay Speech Recognition System

Download
374 downloads
  • @INPROCEEDINGS{10.1007/978-3-319-11629-7_18,
        author={Noraini Seman and Zainab Bakar and Nordin Bakar},
        title={Dynamic Neuro-genetic Weights Connection Strategy for Isolated Spoken Malay Speech Recognition System},
        proceedings={Signal Processing and Information Technology. Second International Joint Conference, SPIT 2012, Dubai, UAE, September 20-21, 2012, Revised Selected Papers},
        proceedings_a={SPIT},
        year={2014},
        month={11},
        keywords={Artificial Neural Network Conjugate Gradient Genetic Algorithm Global Optima Feed-forward Network},
        doi={10.1007/978-3-319-11629-7_18}
    }
    
  • Noraini Seman
    Zainab Bakar
    Nordin Bakar
    Year: 2014
    Dynamic Neuro-genetic Weights Connection Strategy for Isolated Spoken Malay Speech Recognition System
    SPIT
    Springer
    DOI: 10.1007/978-3-319-11629-7_18
Noraini Seman1,*, Zainab Bakar1,*, Nordin Bakar1,*
  • 1: Universiti Teknologi MARA (UiTM)
*Contact email: aini@tmsk.uitm.edu.my, zainab@tmsk.uitm.edu.my, nordin@tmsk.uitm.edu.my

Abstract

This paper presents the fusion of artificial intelligence (AI) learning algorithms that combined genetic algorithms (GA) and neural network (NN) methods. These both methods were used to find the optimum weights for the hidden and output layers of feed-forward artificial neural network (ANN) model. Both algorithms are the separate modules and we proposed dynamic connection strategy for combining both algorithms to improve the recognition performance for isolated spoken Malay speech recognition. 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 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 99%.