Evaluation of English Pronunciation Quality Based on Decision Tree Algorithm

In order to solve the limitations of existing evaluation indexes and methods, English pronunciation quality assessment based on decision tree is proposed. This paper discusses decision tree models similar to a general evaluation process. An ID3 (Interactive Double Inversion 3) algorithm was used to establish an index decision tree including five factors: pitch, rhythm, intonation, speed, and emotion. Based on the test results, the human-machine test accuracy is 73.9%, the similarity is 93.8%, and the Pearson correlation value is 0.81. Conclusion: The evaluation method is reliable.