Syllabification in English through AI: A Comparative Study of ChatGPT and Gemini
DOI:
https://doi.org/10.21271/zjhs.29.SpB.38Keywords:
Syllabification, AI, ChatGPT, GeminiAbstract
This paper examines the English language syllabification task, focusing on two advanced Artificial Intelligence (AI) models: ChatGPT and Gemini. Syllabification is one of the first things one learns about phonology; it is the process of breaking words apart into their smallest phonological units, syllables. It is an essential idea that we will consider for a number of purposes, including language learning, speech synthesis, or computational linguistics, that the systematic view of syllables might help you to teach engineering development in voice recognition and the reaction process. The analysis of transcribed words is based on Peter Roach (RP) in (2009) and the Oxford Advanced Learner's Dictionary (2020). It utilizes a carefully selected dataset comprising 100 multisyllabic English words, covering all lexical categories. Then the words have been carefully analyzed to evaluate the accuracy of segmentation in the syllabification process. Through a comprehensive comparative analysis, the study identified the commonalities and differences in the syllabification patterns exhibited by the two AI models. This study significantly contributes to phonemic research, demonstrating the potential applications and limitations of AI in linguistic contexts, and shows that ChatGPT is more accurate in the task of syllabification than Gemini.
References
- Davis, A. (2024). AI rising in higher education: opportunities, risks and limitations. Asian Education and Development Studies. http://dx.doi.org/10.1108/AEDS-01-2024-0017
- Duanmu, S., Kim, H.-Y., & Stiennon, N. (2005). Stress and Syllable Structure in English: Approaches to Phonological Variations. Taiwan Journal of Linguistics. http://dx.doi.org/10.6519/TJL.2005.3(2).2
- Fakih, H. (2020). The relationship between artificial intelligence and reducing the cognitive load of learners, Zanco Journal of Human Sciences, Vol. 24, No. 5
https://doi.org/10.21271/zjhs.24.s5.34.
- Giegerich, H. J. (1998). English Phonology. Cambridge University Press.
- Ladefoged, P., Johnson, K. (2014). A Course in Phonetics, 6th ed. Cengage Learning.
- McMahon, A. (2002). An Introduction to English Phonology. Edinburgh University Press.
- Mohammadkarimi, E. (2024). Exploring the Use of Artificial Intelligence in Promoting English Language Pronunciation Skills. Journal on Language and Language Teaching 27, 98–115. https://doi.org/10.24071/llt.v27i1.8151
- Parker, S.G. (2002). Quantifying the sonority hierarchy. PhD dissertation. University of Massachusetts Amherst.
- Roach, P. (2009). English Phonetics and Phonology. Cambridge University Press.
- Tian J. (2004). Data-driven Approaches for Automatic Detection of Syllable Boundaries. 8th International Conference on Spoken Language Processing, ICSLP pp. 61-64 http://dx.doi.org/10.21437/Interspeech.2004-60
- Treiman, R. and Zukowski, A. (1990). Toward an understanding of English syllabification. Journal of Memory and Language, 29(1), pp.66–85. http://dx.doi.org/10.1016/0749-596X(90)90010-W
- Vančová, H. (2023). AI and AI-powered tools for pronunciation training. Journal of Language and Cultural Education 11, 12–24. https://doi.org/10.2478/jolace-2023-0022
- Wattpad (n.d.) Sonority Hierarchy. [online] Available at: https://www.wattpad.com/814152454-conlang-001-kjamir-sonority-hierarchy
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Askandar Khalid Abdullah, Pakhshan Ismail Hamad
This work is licensed under a Creative Commons Attribution 4.0 International License.
