The Application of Classifier Model Based on FA-SVM Algorithm in Speech Recognition

Abstract

In recent years, speech recognition technology has been increasingly widely used. How to improve the robustness of speech recognition systems has become the focus of researchers. This paper proposes an accent recognition model based on the Firefly algorithm to optimize the support vector machine. Firstly, a set of penalty factors and kernel parameters in the support vector machine are taken as firefly individuals, and the important parameters affecting the performance of the support vector machine are optimized by the firefly algorithm. A Firefly-Support vector machine (FA-SVM) model is established and applied to accent recognition. The example analysis shows that the FA-SVM accent recognition model has taller classification accuracy and faster running speed than the PSO-SVM and GA-SVM classifier models.