A Thai word pronunciation simulator based on DFT analysis and GA search

Abstract

This paper aims to present and discuss the concept of a Thai word pronunciation simulator based on DFT (Discrete Fourier Transform) analysis and GA (Genetic Algorithm) search. By DFT analysis, the simulator converts the sound of a Thai word from a foreign leaner into its frames to get sound segments. The GA search on the sound segments generates a highest similarity sound value with a standard Thai sound. The GA search is supported by a library of original Thai word sounds. Once the simulator generates a real pronunciation of the leaner's word, it will store the sound data to train the user. The simulations presented in this paper indicate that the proposed approach is one of the most effective strategies of structuring a language trainer.