Dynamic relationship between oral English pronunciation standard and mental health monitored by biosensor
Abstract
Oral English pronunciation is an important feature of language ability, especially among non-native speakers, as good pronunciation has a direct impact on communication efficacy and social integration. However, the difficulties connected with attaining a high standard of oral English pronunciation can lead to severe stress, anxiety, and other mental health disorders. The purpose of the research is to establish a dynamic correlation between oral English pronunciation standards and mental health, as monitored through biosensor data. The research aims to explore how variations in speech accuracy and fluency during English pronunciation tasks can reflect underlying psychological states, such as stress, anxiety, and overall emotional well-being. The study proposed a novel Improved Flower Pollination-tuned Resilient Deep Neural Network (IFP-RDNN) in this article, to predict the oral English pronunciation rating using biosensors. Electroencephalography (EEG)records patterns of cerebral waves using electrodes applied to the head to assess the electrical impulses in the cerebellum called EEG signals was acquired during the listening state and with the audio signals utilized in stimuli, as well as the spoken audio obtained from the subject. The data processing used a median filter to remove noise from the audio data. Fast Fourier transform (FFT) is used to extract the features from the preprocessed data. It is measured by biomedical data, can be predicted with the help of an optimization technique which draws inspiration called IFP helps to optimize the parameters effectively by mimicking natural pollination processes; RDNN is employed with the optimized parameters; it can predict oral English pronunciation ratings. Experimental results reveal that the spoken audio confirms the improvement in pronunciation throughout the trials. In a comparative analysis, the suggested method is assessed with various evaluation measures, such as F1-score (88.9%), recall (91.60%), precision (89.80%), and accuracy (90.3%). The result demonstrated the IFP-RDNN method to predict the oral English pronunciation rating using biosensors. The findings indicate a significant connection between the quality of oral English pronunciation and mental health, with deviations from standard pronunciation being associated with increased stress and emotional suffering.
References
1. Lee, H., 2022. Developing an Approach to Support Instructors to Provide Emotional and Instructional Scaffolding for English Language Learners Through Biosensor-Based Feedback (Doctoral dissertation, University of Maryland, Baltimore County).
2. Cassar, C., McCabe, P. and Cumming, S., 2023. “I still have issues with pronunciation of words”: A mixed methods investigation of the psychosocial and speech effects of childhood apraxia of speech in adults. International Journal of Speech-Language Pathology, 25(2), pp.193-205. 10.1080/17549507.2021.2018496
3. Vanova, M., Aldridge-Waddon, L., Jennings, B., Puzzo, I. and Kumari, V., 2021. Reading skills deficits in people with mental illness: A systematic review and meta-analysis. European Psychiatry, 64(1), p.e19. 10.1192/j.eurpsy.2020.98
4. Feijóo-García, P.G., Zalake, M., de Siqueira, A.G., Lok, B. and Hamza-Lup, F., 2021, September. Effects of virtual humans' gender and spoken accent on users' perceptions of expertise in mental wellness conversations. In Proceedings of the 21st ACM International Conference on Intelligent Virtual Agents (pp. 68-75). 10.1145/3472306.3478367
5. Lundin, N.B., Jones, M.N., Myers, E.J., Breier, A. and Minor, K.S., 2022. Semantic and phonetic similarity of verbal fluency responses in early-stage psychosis. Psychiatry Research, 309, p.114404. 10.1016/j.psychres.2022.114404
6. Zeng, Y., 2021. Application of flipped classroom model driven by big data and neural network in oral English teaching. Wireless Communications and Mobile Computing, 2021(1), p.5828129. 10.1155/2021/5828129
7. Yang, Y., 2023. Machine learning for English teaching: a novel evaluation method. International Journal of Computer Applications in Technology, 71(3), pp.258-264.
8. Zhang, Y., 2022. Multimedia-assisted oral English teaching system based on B/S architecture. International Journal of Continuing Engineering Education and Life Long Learning, 32(6), pp.663-680. 10.1504/IJCEELL.2022.126869
9. Li, S., 2022, December. General Design of Automatic Correction System for English Pronunciation Errors Based on DTW Algorithm. In 2022 IEEE 2nd International Conference on Mobile Networks and Wireless Communications (ICMNWC) (pp. 1-5). IEEE. 10.1109/ICMNWC56175.2022.10031909
10. Fu, Y., Zhang, Z. and Yang, H., 2023. Design of Oral English Teaching Assistant System based on deep belief networks. Soft Computing, 27(22), pp.17403-17418. 10.1007/s00500-023-09211-8
11. Liu, Y. and Quan, Q., 2022. AI recognition method of pronunciation errors in oral English speech with the help of big data for personalized learning. Journal of Information & Knowledge Management, 21(Supp02), p.2240028. 10.1142/S0219649222400287
12. Alduais, A., Alarifi, H.S. and Alfadda, H., 2024. Using Biosensors to Detect and Map Language Areas in the Brain for Individuals with Traumatic Brain Injury. Diagnostics, 14(14), p.1535.
13. Ramzan, M. and Javaid, Z.K., 2023. PSYCHOLOGICAL FACTORS INFLUENCING PASHTO SPEAKING ESL STUDENTS’PRONUNCIATION OF ENGLISH VOWELS. Pakistan Journal of Society, Education and Language (PJSEL), 9(2), pp.52-63.
14. Wang, J., 2020. Speech recognition of oral English teaching based on deep belief network. International Journal of Emerging Technologies in Learning (Online), 15(10), p.100. 10.3991/ijet.v15i10.14041
15. Jing, C., Zhao, X., Ren, H., Chen, X. and Gaowa, N., 2022. An approach to oral English assessment based on intelligent computing model. Scientific Programming, 2022(1), p.4663574. 10.1155/2022/4663574
16. Li, Y. and Huang, G., 2022, April. An English Pronunciation Quality Evaluation Model Based on Multi-dimensional Features. In Journal of Physics: Conference Series (Vol. 2224, No. 1, p. 012061). IOP Publishing. 10.1088/1742-6596/2224/1/012061
17. Geng, L., 2021. Evaluation model of college English multimedia teaching effect based on deep convolutional neural networks. Mobile Information Systems, 2021(1), p.1874584. 10.1155/2021/1874584
18. Zhou, R., He, B., Lu, X., Gu, X., Dai, X., Peng, J. and Xi, Y., 2023. Research on the Integration of Natural Phonetic Pronunciation and International Phonetic Alphabet to Improve College Students' Oral English Expression Ability. Lecture Notes on Language and Literature, 6(15), pp.38-43. 10.23977/langl.2023.061507
19. Sharma, L.R., 2021. Significance of teaching the pronunciation of segmental and suprasegmental features of English. Interdisciplinary Research in Education, 6(2), pp.63-78. 10.3126/ire.v6i2.43539
20. Wang, Y. and Zhao, P., 2020. A probe into spoken English recognition in English education based on computer-aided comprehensive analysis. International Journal of Emerging Technologies in Learning (iJET), 15(3), pp.223-233.
21. Liang, E. and Ye, S., 2023. The influence of gender differences on Chinese English learners’ oral ability. Journal of Education, Humanities and Social Sciences, 8, pp.813-818. 10.54097/ehss.v8i.4365
22. Iskandar, I., Dewanti, R., Sulistyaningrum, S.D. and Santosa, I., 2024. Scaffolding Assignments to Conciliate the Disinclination to Employ Project-Based Learning of English Pronunciation and Autodidacticism. International Journal of Language Education, 8(2), pp.199-227.
23. Wu, H. and Sangaiah, A.K., 2021. Oral English Speech Recognition Based on Enhanced Temporal Convolutional Network. Intelligent Automation & Soft Computing, 28(1). 10.32604/iasc.2021.016457
24. Gui, L., 2020. An analysis of the strategies for developing students' consciousness of pronunciation and intonation in college English teaching based on international communication. In E3S Web of Conferences (Vol. 214, p. 01041). EDP Sciences. 10.1051/e3sconf/202021401041
25. Huang, A., 2024. Speech Recognition Based on Mobile Biosensor Networks and Quality Evaluation of University Political Education. International Journal of High-Speed Electronics and Systems, p.2540128.
26. Wu, J.Y., Ching, C.T.S., Wang, H.M.D. and Liao, L.D., 2022. Emerging wearable biosensor technologies for stress monitoring and their real-world applications. Biosensors, 12(12), p.1097.
Copyright (c) 2024 Xuan Zhou, Wei Jia, Cuiping Shi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright on all articles published in this journal is retained by the author(s), while the author(s) grant the publisher as the original publisher to publish the article.
Articles published in this journal are licensed under a Creative Commons Attribution 4.0 International, which means they can be shared, adapted and distributed provided that the original published version is cited.
Submit a Paper
