Comparing Human and AI Judgments of Turkish EFL Learners’ Intelligibility

Yıl 2026, Cilt: 39 Sayı: 1 , 33 - 49 , 30.04.2026

Canan Deveci

https://doi.org/10.19171/uefad.1728485

https://izlik.org/JA25AY83JE

Öz

This study investigates how the intelligibility of Turkish learners of English as a foreign language (EFL) is assessed by both human raters and artificial intelligence (AI), specifically ChatGPT-4, across two different speaking tasks: a controlled read-aloud passage and a spontaneous picture-description task. Drawing on intelligibility-focused pronunciation research, the study aims to explore how task type, rater type, and pronunciation features (segmental and suprasegmental) affect intelligibility ratings. 30 intermediate-level Turkish learners of English completed both tasks, and their recordings were evaluated by three native English-speaking human raters and an AI model. Quantitative results showed that spontaneous speech received higher intelligibility scores than the read-aloud task, despite including more segmental errors. Suprasegmental features such as rhythm, stress, and phrasing played a greater role in determining intelligibility across tasks. While AI ratings closely matched human judgments in most cases, discrepancies emerged, particularly in samples where prosodic nuances were critical. Qualitative analysis further revealed that both rater types frequently flagged vowel distortions, stress misplacement, and a lack of rhythmic cohesion as common intelligibility detractors. The findings underscore the importance of integrating suprasegmental instruction in EFL pronunciation pedagogy and highlight the potential role of AI tools in supporting intelligibility assessment. Nevertheless, when it comes to assessing natural, prosody-rich speech, human judgment is still crucial. By providing empirical evidence from a Turkish EFL environment and linking L2 pronunciation research with emerging technology, this study contributes to applied linguistics.

Anahtar Kelimeler

Intelligibility , Pronunciation , Turkish EFL learners , AI , ChatGPT

Etik Beyan

Ethics committee approval was obtained for the research at the meeting of Ataturk University Social and Human Sciences Ethics Committee numbered E.88656144-000-2500199482.

İngilizceyi Yabancı Dil Olarak Öğrenen Türk Öğrencilerin Konuşma Anlaşılırlığının İnsan ve Yapay Zekâ Değerlendirmeleriyle Karşılaştırılması

https://izlik.org/JA25AY83JE

Öz

Bu çalışma, İngilizceyi yabancı dil olarak öğrenen Türk öğrencilerin İngilizce konuşma anlaşılırlığının insan değerlendiriciler ve yapay zeka (ChatGPT-4) tarafından biri kontrollü okuma ve diğeri serbest resim betimleme olmak üzere iki farklı konuşma görevi üzerinden nasıl değerlendirildiğini incelemektedir. Anlaşılırlık odaklı sesletim araştırmalarından hareketle, çalışmada görev türü, değerlendirici türü ve sesletim özelliklerinin (parçalı ve parçalarüstü ses birim) anlaşılırlık puanlarını nasıl etkilediği araştırılmıştır. Orta düzeyde İngilizce yeterliliğe sahip 30 Türk öğrenci her iki görevi tamamlamış ve ses kayıtları anadili İngilizce olan üç değerlendirici ve bir yapay zeka sürümü olan ChatGPT-4 tarafından değerlendirilmiştir. Nicel bulgular, serbest resim betimleme görevinin parçalı sesbirim hatalarını daha fazla barındırmasına rağmen okuma görevine kıyasla daha yüksek anlaşılırlık puanları aldığını göstermiştir. Özellikle ritim, vurgu ve söz gruplaması gibi parçalarüstü ses birim özelliklerin anlaşılırlığın belirlenmesinde daha etkili olduğu görülmüştür. Yapay zeka puanlamaları çoğu durumda insan değerlendirmeleriyle yakınlık göstermiş, ancak özellikle prosodi ayrıntıların kritik olduğu örneklerde farklılıklar ortaya çıkmıştır. Nitel analiz, her iki değerlendirici türünün de sıkça ünlü ses bozulmaları, yanlış vurgu ve ritmik bütünlük eksikliğini anlaşılırlığı düşüren unsurlar olarak işaretlediğini ortaya koymuştur. Bulgular, İngilizce öğretiminde parçalarüstü ses birim özelliklerin daha güçlü biçimde ele alınması gerektiğini vurgulamakta ve anlaşılırlık değerlendirmesinde yapay zeka araçlarının potansiyel rolüne dikkat çekmektedir. Bununla birlikte, özellikle prosodi açısından daha zengin olan serbest konuşma değerlendirilmesinde insan yargısı vazgeçilmezdir. Bu çalışma, ikinci dil sesletim araştırmalarını gelişen teknolojilerle buluşturarak uygulamalı dilbilime katkı sağlamakta ve yabancı dil olarak İngilizce öğretimi bağlamından deneysel kanıtlar sunmaktadır.

Anahtar Kelimeler

Anlaşılırlık , Sesletim , İngilizceyi yabancı dil olarak öğrenen Türk öğrenciler , Yapay zeka , ChatGPT

Etik Beyan

Araştırma için etik kurul onayı, E.88656144-000-2500199482 sayılı Atatürk Üniversitesi Sosyal ve Beşeri Bilimler Etik Kurulu toplantısında alınmıştır.

Kaynakça

• Aoyama, K., & Guion, S. G. (2007). Prosody in second language acquisition: Acoustic analyses of duration and F0 range. In O.-S. Bohn & M. J. Munro (Eds.), Language experience in second-language speech learning (pp. 282–297). John Benjamins.
• Babaeian, A. (2023). Pronunciation assessment: Traditional vs modern modes. Journal of Education For Sustainable Innovation, 1(1), 61-68. https://doi.org/10.56916/jesi.v1i1.530
• Bayraktaroğlu, S. (2008). Orthographic interference and the teaching of British pronunciation to Turkish learners. Journal of Language and Linguistic Studies, 4(2), 1-36.
• Celce Murcia, M., Brinton, D. M., Goodwin, J. M., & Griner, B. (2010). Teaching pronunciation: A course book and reference guide (2nd ed.). Cambridge University Press.
• Chau, T., Huensch, A., Hoang, Y. K., & Chau, H. T. (2022). The effects of L2 pronunciation instruction on EFL learners’ intelligibility and fluency in spontaneous speech. TESL EJ, 25(4), n4.
• Demirezen, M. (2005). Rehabilitating a fossilized pronunciation error: The/v/and/w/contrast by using the audio-articulation method in teacher training in Türkiye. Journal of Language and Linguistic Studies, 1(2), 183-192.
• Derwing, T. M., & Munro, M. J. (1995). Foreign accent, comprehensibility, and intelligibility in L2 learner speech. Language Learning, 45(1), 73–97. https://doi.org/10.1111/j.1467-1770.1995.tb00963.x
• Derwing, T. M., & Munro, M. J. (1997). Accent, intelligibility, and comprehensibility: Evidence from four L1s. Studies in second language acquisition, 19(1), 1-16. https://doi.org/10.1017/S0272263197001010
• Derwing, T. M., & Munro, M. J. (2009). Putting accent in its place: Rethinking obstacles to communication. Language teaching, 42(4), 476-490. https://doi.org/10.1017/S026144480800551X
• Derwing, T. M., & Munro, M. J. (2015). Pronunciation fundamentals: Evidence based perspectives for L2 teaching and research. John Benjamins.
• Dörnyei, Z. (2007). Research methods in applied linguistics. Oxford university press.
• Dikilitaş, K., & Geylanioğlu, S. (2019). Pronunciation Errors of Turkish Learners of English: Conceptualization Theory as a Teaching Method. Journal of Language Teaching and Learning, 2(2), 38-50. Retrieved from https://www.jltl.com.tr/index.php/jltl/article/view/101
• Ercan, H. (2018). Pronunciation Problems of Turkish EFL Learners in Northern Cyprus. International Online Journal of Education and Teaching, 5(4), 877-893. International Online Journal of Education and Teaching, v5 n4 p877- 893 2018
• Fairbanks, G. (1960). Voice and articulation drillbook (2nd ed.). Harper & Row.
• Field, J. (2005). Intelligibility and the listener: The role of lexical stress. TESOL Quarterly, 39(3), 399–423. https://doi.org/10.2307/3588487
• Foote, J. A., Holtby, A. K., & Derwing, T. M. (2011). Survey of the teaching of pronunciation in adult ESL programs in Canada, 2010. TESL Canada journal, 1-22. https://doi.org/10.18806/tesl.v29i1.1086
• Geng, H., Saito, D., & Minematsu, N. (2025). A perception-based L2 speech intelligibility Indicator: Leveraging a rater’s shadowing and sequence-to-sequence voice conversion. arXiv preprint arXiv:2505.24304. https://doi.org/10.48550/arXiv.2505.24304
• Hahn, L. (2004). Primary stress and intelligibility: Research to motivate the teaching of suprasegmentals. TESOL Quarterly, 38(2), 201–223. https://doi.org/10.2307/3588378
• Hismanoglu, M. (2012). Teaching word stress to Turkish EFL learners through Internet-based video lessons. US–China Education Review A, 1(26), 26–40.
• Jenkins, J. (2000). The phonology of English as an international language. Oxford University Press.
• Kang, O., Rubin, D., & Pickering, L. (2010). Suprasegmental measures of accentedness and judgments of 1107 language learner proficiency in oral English. Modern Language Journal, 94(4), 554–566. https://doi.org/10.1111/j.1540-4781.2010.01091.x
• Khalilzadeh, A. (2014). Phonetic and non-phonetic languages: A contrastive study of English and Turkish phonology focusing on the orthography-induced pronunciation problems of Turkish learners of English as a foreign language (Turkish EFL learners). International Journal of Languages’ Education and Teaching, 2(1), 1-16.
• Kheir, Y. E., Ali, A., & Chowdhury, S. A. (2023). Automatic pronunciation assessment--a review. arXiv preprint arXiv:2310.13974. https://doi.org/10.48550/arXiv.2310.13974
• Kormos, J., & Dénes, M. (2004). Exploring measures and perceptions of fluency in the speech of second language learners. System, 32(2), 145–164. https://doi.org/10.1016/j.system.2004.01.001
• Lee, J., Jang, J., & Plonsky, L. (2015). The effectiveness of second language pronunciation instruction: A meta-analysis. Applied Linguistics, 36(3), 345–366. https://doi.org/10.1093/applin/amu040
• Levis, J. M. (2005). Changing contexts and shifting paradigms in pronunciation teaching. TESOL Quarterly, 39(3), 369–377. https://doi.org/10.2307/3588485
• Levis, J. M. (2018). Intelligibility, oral communication, and the teaching of pronunciation. Cambridge: Cambridge University Press. https://doi.org/10.1017/9781108241564
• Levis, J. (2020). Revisiting the intelligibility and nativeness principles. Journal of Second Language Pronunciation, 6(3), 310–328. https://doi.org/10.1075/jslp.20050.lev
• Lochland, P. (2020). Intelligibility of L2 Speech in ELF. Australian Journal of Applied Linguistics, 3(3), 196-212.
• Mompean, J. A. (2024). ChatGPT for L2 pronunciation teaching and learning. ELT Journal, 78(4), 423-434. https://doi.org/10.1093/elt/ccae050
• Munro, M. J., & Derwing, T. M. (1995). Foreign accent, comprehensibility, and intelligibility in the speech of second language learners. Language Learning, 45(1), 73–97. https://doi.org/10.1111/j.1467-1770.1995.tb00963.x
• Munro, M. J., & Derwing, T. M. (2020). Foreign accent, comprehensibility and intelligibility, redux. Journal of Second Language Pronunciation, 6(3), 283-309. https://doi.org/10.1075/jslp.20038.mun
• Munro, M. J., Derwing, T. M., & Morton, S. L. (2006). The mutual intelligibility of L2 speech. Studies in second language acquisition, 28(1), 111-131. https://doi.org/10.1017/S0272263106060049
• Pease, C. (2016). Accentedness, comprehensibility and intelligibility of L2 speech: A replication and extended study (Doctoral dissertation, University of York).
• Saito, K. (2012). Effects of instruction on L2 pronunciation development: A synthesis of 15 quasi-experimental intervention studies. TESOL Quarterly, 46(4), 842–854. https://doi.org/10.1002/tesq.67
• Saito, K. (2018). Advanced second language segmental and suprasegmental acquisition. The handbook of advanced proficiency in second language acquisition, 282-303. https://doi.org/10.1002/9781119261650.ch15
• Seidlhofer, B. (2013). Understanding English as a lingua franca. Oxford University Press.
• Somasundaran, S., Chen, L., Cheng, X., & Zechner, K. (2015). Exploring content and discourse features for automated speech scoring. Proceedings of the Tenth Workshop on Innovative Use of NLP for Building Educational Applications, 12–21. https://doi.org/10.3115/v1/W15-0602
• Uzun, T. (2022). The salient pronunciation errors and intelligibility of Turkish speakers in English. MEXTESOL Journal, 46(1), 1–15. https://doi.org/10.61871/mj.v46n1-9
• Vančová, H. (2023). AI and AI-powered tools for pronunciation training. Journal of Language and Cultural Education, 11(3), 12-24.
• Yavaş, M. (2011). Applied english phonology (2nd ed.). Wiley-Blackwell.
• Yorkston, K. M., Beukelman, D. R., & Traynor, C. (1984). Assessment of intelligibility of dysarthric speech. Austin, TX: Pro-ed.
• Zechner, K., Higgins, D., Xi, X., & Williamson, D. M. (2009). Automatic scoring of non-native spontaneous speech in tests of spoken English. Speech communication, 51(10), 883-895. https://doi.org/10.1016/j.specom.2009.04.009
• Zou, B., Liviero, S., Ma, Q., Zhang, W., Du, Y., & Xing, P. (2024). Exploring EFL learners’ perceived promise and limitations of using an artificial intelligence speech evaluation system for speaking practice. System, 126, 103497. https://doi.org/10.1016/j.specom.2009.04.011