In today's world economic integration and internationalization process is accelerating, the demand for improving English teaching and English pronunciation is also increasing rapidly. In this paper, deep learning techniques were applied to the evaluation of English pronunciation level, and Deep Belief Networks (DBN) were used to build English pronunciation level models. Therefore, according to the characteristics of Chinese college students' English pronunciation, this paper improved the traditional computer English pronunciation quality evaluation method, and comprehensively evaluated various evaluation indicators such as intonation, speech speed, rhythm, and intonation. The tests showed that the English pronunciation quality evaluation model had high credibility as evidenced by the 88.33% total agreement rate between machine evaluation and manual evaluation and the 0.723 Pearson correlation coefficient, and it could evaluate and give feedback in a timely, accurate and objective manner. This helped learners find the difference between their pronunciation and standard pronunciation and correct their English pronunciation in time, thereby improving their English pronunciation.

Jing Cheng. Modular Design of English Pronunciation Level Evaluation System Based on Deep Learning. International Journal of New Developments in Education (2025), Vol. 7, Issue 4: 146-155. https://doi.org/10.25236/IJNDE.2025.070421.

[1] Abbasinia S and Pouralvar K. Evaluation of Speech Processing Capability in Computer Games to Improve the Process of Learning English Pronunciation: An Action Research. Journal of Rehabilitation Sciences, 2019, 15(5):280-285.

[2] Davila A M. Using the Shadowing Technique to Improve Ecuadorian English Learners' Speaking Intelligibility 1, Angel M. Dávila and International Journal of Current Research, 2018, 10(12):76770-76772.

[3] Li X. Characteristics and rules of college English education based on cognitive process simulation. Cognitive Systems Research, 2019, 57(OCT.):11-19. https://doi.org/10.1016/j.cogsys.2018.09.014

[4] Chika, Fujiyuki, Sayoko. An Evaluation of English Pronunciation of Japanese EFL Learners Using Multiple Metrics. Journal of the Phonetic Society of Japan, 2018, 22(2):39-43.

[5] Piotrowska M, Czyewski A, Ciszewski T. Evaluation of aspiration problems in L2 English pronunciation employing machine learning. The Journal of the Acoustical Society of America, 2021, 150(1):120-132. https://doi.org/10.1121/10.0005480

[6] Lasi F. A Study on the Ability of Supra-Segmental and Segmental Aspects in English Pronunciation. Ethical Lingua Journal of Language Teaching and Literature, 2020, 7(2):426-437. https://doi.org/10.30605/25409190.222

[7] Wang X. The framework of the multi-parameter evaluation index system for college spoken english based on deep learning theory. Revista de la Facultad de Ingenieria, 2017, 32(15):583-590.

[8] Suparman U, Ridwan R and Hariri H. Overcoming Students' English Pronunciation in Remote Area, Indonesia. Asian EFL Journal, 2020, 27(4):213-229.

[9] Gu X. A study on college students' english level evaluation model based on cloud services platform. Boletin Tecnico/Technical Bulletin, 2017, 55(4):299-305.

[10] Han Y. Evaluation of English online teaching based on remote supervision algorithms and deep learning. Journal of Intelligent and Fuzzy Systems, 2020, 01(5):1-12.

[11] Rani S, Tina A A. The Impact of Bangla Regional Dialect on the Pronunciation of English at Tertiary Level. Humanities & Social Sciences Reviews, 2020, 8(2):513-522. https://doi.org/10.18510/hssr.2020.8259

[12] Zhou W, Deterding D and Nolan F . Intelligibility in Chinese English Spoken in Central China. Chinese Journal of Applied Linguistics, 2019, 42(4):449-465. https://doi.org/10.1515/CJAL-2019-0027

[13] Maslova A and Kolesnikova A. Through the eyes of high school students: Which English pronunciation norm to study in Russia? Vestnik - Moskvoskogo Universiteta, 2019, 19(2):115-123.

[14] Suciati S and Diyanti Y. Suprasegmental Features of Indonesian Students' English Pronunciation and the Pedagogical Implication. SAGA Journal of English Language Teaching and Applied Linguistics, 2021, 2(1):9-18. https://doi.org/10.21460/saga.2020.21.62

[15] Phuong T. Who Should Teach English Pronunciation? -Voices of Vietnamese EFL Learners and Teachers. Journal of Asia TEFL, 2021, 18(1):125-141. https://doi.org/10.18823/asiatefl.2021.18.1.8.125

[16] Thanh T. Vietnamese EFL Learners' Perspectives of Pronunciation Pedagogy. Asian EFL Journal, 2019, 23(6):180-201. 

[17] Wu X. AHP-BP-Based Algorithms for Teaching Quality Evaluation of Flipped English Classrooms in the Context of New Media Communication. International Journal of Information Technologies and Systems Approach, 2023, 16(2), 1-12.