A method of English-Chinese language recognition and its application in oral English learning system
Xinguang Li, Shuai Chen, Zhichao Zhou, Xiaolan Long, ZeMing Chen, Weiyuan Wu · Proceedings of the 2020 4th International Conference on Electronic Information Technology and Computer Engineering · 2020
In this paper, Gammatone Frequency Cepstrum Coefficients (GFCC) and Shifted Delta Cepstra (SDC) hybrid model were used to extract the speech feature parameters, and Gaussian Mixture Model-Universal Background Model (GMM-UBM) was used for language recognition. Taking oral English speeches of Chinese students as a corpus, we developed an English-Chinese language recognition module and applied it to the oral English learning system. The module could identify whether the student's answer language was English, which could increase the intelligence of the learning system. The experiment results showed the language recognition system introduced in this paper had a higher recognition accuracy and enhanced the function of the learning system.