As the most widely used language in the world, English has always had the largest number of learners. Therefore, this study has a practical foundation for the recognition of English stressed syllables. As is well known, listening and speaking are crucial aspects of language learning, as they are directly related to communication. Therefore, this article aimed to design a mature syllable recognition algorithm and assist it based on neural prediction models. In the end, this article used the algorithm system for a month of auxiliary training for a certain English major class, and conducted a comparative test on phrase recognition rate and pronunciation accuracy before and after. The results showed that the phrase recognition rate increased from 89.34% to 96.05%, and the pronunciation accuracy rate increased from 73.65% to 92.84%, comprehensively improving students' English learning ability.

Qingjiao Lu. Recognition and Evaluation Algorithm for English Pronunciation Syllables Based on Neural Prediction Model. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 10: 48-53. https://doi.org/10.25236/AJCIS.2023.061008.

[1] Mol C, Bolhuis J J, Moorman S. Vocal learning in songbirds: the role of syllable order in song recognition. Philosophical Transactions of the Royal Society B, 2021, 376(1836): 1-7

[2] Flo A, Benjamin L, Palu M, et al. Sleeping neonates track transitional probabilities in speech but only retain the first syllable of words. Scientific reports, 2022, 12(1): 1-13

[3] Campos A D, Oliveira H M, Soares A P. Syllable effects in beginning and intermediate European-Portuguese readers: Evidence from a sandwich masked go/no-go lexical decision task. Journal of Child Language, 2021, 48(4): 699-716

[4] Brennan M A, McCreery R W, Massey J. Influence of audibility and distortion on recognition of reverberant speech for children and adults with hearing aid amplification. Journal of the American Academy of Audiology, 2022, 33(3): 170-180

[5] Anand C. Comparison of stock price prediction models using pre-trained neural networks. Journal of Ubiquitous Computing and Communication Technologies (UCCT), 2021, 3(2): 122-134

[6] Chae S, Shin J, Kwon S, et al. PM10 and PM2. 5 real-time prediction models using an interpolated convolutional neural network. Scientific Reports, 2021, 11(1): 1-9

[7] Ramirez-Mendoza A M E, Yu W, Li X. A new spike membership function for the recognition and processing of spatiotemporal spike patterns: syllable-based speech recognition application. Mathematics, 2023, 11(11): 1-28

[8] Khanzadi M, Veisi H, Alinaghizade R, et al. Persian phoneme and syllable recognition using recurrent neural networks for phonological awareness assessment. Journal of AI and Data Mining, 2022, 10(1): 117-126

[9] Pahuja H, Ranjan P, Ujlayan A, et al. Convolution Neural Network Based Visual Speech Recognition System for Syllable Identification. Recent Advances in Computer Science and Communications (Formerly: Recent Patents on Computer Science), 2022, 15(1): 139-150

[10] Wang D, Zeng M, Zhao H, et al. Effects of syllable boundaries in Tibetan reading. Scientific Reports, 2023, 13(1): 1-10

[11] Zhou P. Analysis and Solution of English Majors' Oral Pronunciation Errors and Vocabulary. Modernization of Education, 2018, 5(29):170-171

[12] Quoc T X, Thanh V Q, Dang T D M, et al. Teachers' perspectives and practices in teaching English pronunciation at Menglish center. International Journal of TESOL & Education, 2021, 1(2): 158-175

[13] Minkova D, Lefkowitz M. Middle English Open Syllable Lengthening (MEOSL) or Middle English Compensatory Lengthening (MECL)? English Language & Linguistics, 2021, 25(1): 155-180

[14] Shang W J, Wang G H. Application of Mind Mapping in English Learning Strategies. Journal of Changchun Normal liniversily, 2018, 37(1):183-186

[15] Zhang R P, Jiang Z C. Tibetan syllable recognition algorithm based on the features. Electronic Design Engineering, 2018, 26(20):137-142

[16] Fan W, Han J G, Gou F, Li S. Chinese character CAPTCHA recognition based on convolution neural network. Computer Engineering and Applications, 2018, 54(3):160-165

[17] Fan H, Zhang X M, Mei S W, Zhang Z L. A spatiotemporal neural network-based ultra-short term wind speed prediction model for wind farms. Automation of Electric Power Systems, 2021, 45(1):28-35

[18] Sarvamangala D R, Kulkarni R V. Convolutional neural networks in medical image understanding: a survey. Evolutionary intelligence, 2022, 15(1): 1-22

[19] Ni Q, Ji J C, Feng K. Data-driven prognostic scheme for bearings based on a novel health indicator and gated recurrent unit network. IEEE Transactions on Industrial Informatics, 2022, 19(2): 1301-1311

[20] Atmowardoyo H, Weda S, Sakkir G. Learning Strategies in English Skills used by Good Language Learners in Millennial Era: A Positive Case Study in Universitas Negeri Makassar. ELT Worldwide, 2021, 8(1): 28-40 

[21] Sujanta Kazemanzadeh. Distributed System Integrating Virtual Reality Technology in English Teaching. Distributed Processing System (2022), Vol. 3, Issue 1: 62-70.