English learning system of oral phonation based on phoneme and smart phone platform

Design a software system on smart phone platform. The purpose of this system is providing a reasonable method to evaluate the English accent of non-native speakers, based on the phoneme recognition and fluency assessment, taking advantage of Hidden Markov Model (HMM). Meanwhile, this paper would use the neural net algorithm to combine the objective scoring and experts´ scoring to increase the accuracy of the system. Moreover, by using this system, factors which are more important in oral English evaluation can be found.