Authors : Aymen Mnassri, Adnane Cherif and Mohammed Bennasr
Abstract: In order to improve the accuracy of Arabic speech recognition, this study proposes a novel recognition technique (ASR) based on GA optimized SVM multi-class algorithm. The Kernel parameters of support vector machine are very important problems that have a great influence on the performance of recognition rate. Thus, GA is adapted to optimize the penalty parameter C and the kernel parameter γ for SVM multi-class which leads to improved classification performance. Finally, the proposed model is tested experimentally using eleven Arabic words mono-locutor. Each word of them is improved by Mel Frequency Cepstral Coefficients (MFCCs) and used as an input to the SVM multi-class classifier. The proposed method enhances the recognition rate which is performed to 100% within short duration training time.
Aymen Mnassri, Adnane Cherif and Mohammed Bennasr, 2019. GA Algorithm Optimizing SVM Multi-Class Kernel Parameters Applied in Arabic Speech Recognition. International Journal of Signal System Control and Engineering Application, 12: 85-92.