Abstract This paper combines machine learning with acoustic features to design an automatic pronunciation error correction system. The article first adopts Meier’s inverse spectral coefficients and random forest algorithm to classify and detect learners’ pronunciation errors and clarify learners’ pronunciation problems, from which the MFCC-RF model is proposed. Then, using the feature self-learning capability of deep belief networks and the OneClass idea of SVM, we proposed a DBN-SVM model to overcome the shortcomings of the MFCC-RF model in pronunciation classification and error detection due to unbalanced samples and missing data, which resulted in low error detection rate and poor coverage of error types. By comparing the model’s performance for pronunciation error detection, the DBN-SVM model was more accurate than the other two algorithms in detecting the three error types with a stable accuracy of around 80%. Finally, when the experimental class was taught with the automatic pronunciation error correction system, the experimental class improved by 19.5 points after one semester of study, while the control class only improved by 6.8 points. Hence, the DBN-SVM model-based pronunciation mistake correction system has significantly impacted the speed of change and advancement in English teaching techniques while substantially enhancing the quality of oral pronunciation and learning efficiency of English learners.
Read full abstract