Study of Artificial Intelligence-Assisted English Oral Teaching
DOI:
https://doi.org/10.54691/8965yk53Keywords:
Artificial Intelligence; Large Language Models; Text-to-Speech; Sentence Length; Speech Rate.Abstract
This study investigates and practices the auxiliary role of Artificial Intelligence (AI) technology, especially Large Language Models (LLM) and Text-to-Speech (TTS) technology, in English oral teaching. In the study, an AI-based LLM oral dialogue platform was constructed to replace teachers for one-on-one interactive training with students. It has been applied in college English teaching in various universities, and teaching data has been collected and analyzed in real-time. The effectiveness of AI technology in assisting college English oral teaching was evaluated, and the role of AI technology application in improving students' oral skills was explored. We conducted comparative analysis on indicators such as the speaking sentence length, speech rate, and combined with questionnaires from students, we surveyed the practical effects of AI oral teaching. The study shows that AI-assisted dialogue training has a significant positive effect on college English oral skills, and we have also proposed corresponding teaching strategies and suggestions.
Downloads
References
[1] G. L. Liu, R. Darvin, and C. Ma, (2024) ‘Exploring AI-mediated informal digital learning of English (AI-IDLE): a mixed-method investigation of Chinese EFL learners’ AI adoption and experiences’, Computer Assisted Language Learning, p. 1–29.
[2] X. Zhang, J. Sun, & Y. Deng. Design and Application of Intelligent Classroom for English Language and Literature Based on Artificial Intelligence Technology. Applied Artificial Intelligence, Vol. 37(2023) p. 1553-1575.
[3] A. Baevski, S. Edunov, Y. H. Liu, L. Zettlemoyer, and M. Auli. 2019. Cloze-driven Pretraining of Self-attention Networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), p. 5360–5369.
[4] T. B. Brown, et al. Language Models are Few-Shot Learners. NIPS'20: Proceedings of the 34th International Conference on Neural Information Processing Systems, Article No.: 159, P. 1877 - 1901.
[5] R. Shadiev, W. Y. Hwang, N. S. Chen and Y. M. Huang. Review of speech-to-text recognition technology for enhancing learning. Journal of Educational Technology & Society, Vol. 17(4), p. 65–84.
[6] D. Nickolai, E. Schaefer, and P. Figueroa, Aggregating the evidence of automatic speech recognition research claims in CALL, System, Vol. 121, p.103250-103260.
[7] S. S. Manathunga, Y. A. Illangasekara. Retrieval Augmented Generation and Representative Vector Summarization for large unstructured textual data in Medical Education. Information on https://doi.org/10.48550/arXiv.2308.00479.
[8] M. Darling-White and S. Banks. Speech Rate Varies With Sentence Length in Typically Developing Children. Journal of speech, language, and hearing research, Vol. 64(2021), P. 2385-2391.
[9] R. L. Street and R. M. Brady (1982). Speech rate acceptance ranges as a function of evaluative domain, listener speech rate, and communication context. Communication Monographs, Vol. 49(1982), p. 290–308.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Scientific Journal of Intelligent Systems Research
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.