İngilizce Öğrencilerinin Kelime Düzeyinde Anlaşılabilirliğinin Otomatik Konuşma Tanıma Yöntemiyle Veri Temelli İncelenmesi

Öz

Bu çalışma, Türk EFL (İngilizceyi yabancı dil olarak öğrenen) öğrencilerinin konuşmalarında kelime düzeyindeki anlaşılırlığı, bir tanılayıcı araç olarak Otomatik Konuşma Tanıma (ASR) teknolojisini kullanarak incelemektedir. Toplamda 54 üniversite öğrencisi, üç ayrı okuma oturumunda 100 yaygın olarak yanlış telaffuz edilen İngilizce kelimeyi içeren metinleri seslendirmiştir. ASR tarafından üretilen transkripsiyonlar, anlaşılırlık oranlarını, hata türlerini ve yerine geçen kelime örüntülerini belirlemek üzere analiz edilmiştir. Genel anlaşılırlık oranı %71,2 olarak bulunmuş, katılımcılar ve hedef kelimeler arasında anlamlı farklılıklar gözlenmiştir. Türkçede bulunmayan bazı sesleri (/θ/, /æ/ gibi) içeren kelimeler sıklıkla anlaşılamazken, geleneksel olarak “zor” kabul edilen bazı kelimeler anlaşılır çıkmıştır. Hata analizleri, en yaygın anlaşılırlık sorunlarının “yanlış kelime” ile yer değiştirme şeklinde olduğunu ortaya koymuş, bazı hataların ciddi anlamsal ya da sosyal sonuçlar doğurduğu belirlenmiştir. Geri bildirim veya öğretim olmamasına rağmen, oturumlar arasında anlaşılırlık oranında mütevazı bir artış gözlemlenmiş, bu da tekrar eden sözlü üretimin olası yararlarına işaret etmektedir. Elde edilen bulgular, sabit “zor kelime” listelerinin geçerliliğini sorgulamakta ve ASR temelli, bağlama duyarlı telaffuz değerlendirme ve öğretim yaklaşımlarının gerekliliğini desteklemektedir.

Anahtar Kelimeler

• Intelligibility
• pronunciation
• Turkish EFL learners
• automatic speech recognition (ASR)
• commonly mispronounced words

An Analysis of Word-Level Intelligibility in EFL Learners Using ASR

Öz

This study investigates word-level intelligibility in the speech of Turkish EFL learners using Automatic Speech Recognition (ASR) as a diagnostic tool. A total of 54 university students read 100 commonly mispronounced English words embedded in three reading sessions. Transcriptions generated by ASR were analyzed to determine intelligibility rates, error types, and substitution patterns. The overall intelligibility rate was 71.2%, with substantial variation across participants and target words. While several words involving phonemes absent in Turkish (e.g., /θ/, /æ/) were frequently unintelligible, others traditionally labeled as difficult proved to be intelligible. Error analysis revealed that the most frequent intelligibility failures were wrong-word substitutions, some of which carried serious semantic or social consequences. Despite the absence of feedback or instruction, intelligibility rates improved modestly across sessions, suggesting potential benefits from repeated oral production. These findings challenge the validity of static “difficult word” lists and support the use of ASR-based, context-sensitive approaches for pronunciation evaluation and pedagogy.

Anahtar Kelimeler

• Intelligibility
• pronunciation
• Turkish EFL learners
• automatic speech recognition (ASR)
• commonly mispronounced words

Kaynakça

1. Baran-Łucarz, M., Czajka, E. and Cardoso, W. (2015). Teaching English phonetics with a learner response system. In W. Sobkowiak (Ed.), Teaching and researching the pronunciation of English: Studies in honour of Włodzimierz Sobkowiak in (pp. 35–61). Springer. https://doi.org/10.1007/978-3-319-11092-9_3
2. Bardakçı, M. (2015). Turkish EFL pre-service teachers’ pronunciation problems. Educational Research and Reviews, 10(16), 2370–2378. https://doi.org/10.5897/ERR2015.2396
3. Boran, G. (2005). Common pronunciation problems of Turkish learners of English. Hacettepe University Journal of Education, 29, 12–20.
4. Chiu, Y.-H., Chang, L. and Hsieh, C.-C. (2021). Using automatic speech recognition to evaluate and improve L2 pronunciation. Computer Assisted Language Learning, 34(5–6), 565–587.
5. Cogo, A. (2012). English as a lingua franca: Concepts, use, and implications. ELT Journal, 66(1), 97–105. https://doi.org/10.1093/elt/ccr090
6. Cunningham, U. (2014). Teaching pronunciation: The case of Turkish learners. Procedia - Social and Behavioral Sciences, 158, 104–111.
7. Derwing, T. M. and Munro, M. J. (1997). Accent, intelligibility, and comprehensibility. Studies in Second Language Acquisition, 19(1), 1–16. https://doi.org/10.1017/S0272263197001012
8. Fraser, H. (2000). Coordinating improvements in pronunciation teaching for adult learners of English as a second language. Department of Education, Training and Youth Affairs.

9. Gilakjani, A. P. and Sabouri, N. B. (2016). How can EFL teachers help EFL learners improve their English pronunciation?. Journal of Language Teaching and Research, 7(5), 967.
10. Hung, J. (2002). Intelligibility and world Englishes in the Asian context. Asian Englishes, 5(2), 4–17.
11. Isaacs, T., and Trofimovich, P. (2012). Deconstructing comprehensibility. Studies in Second Language Acquisition, 34(3), 475–505. https://doi.org/10.1017/S0272263112000150
12. Jenkins, J. (2000). The phonology of English as an international language. Oxford, England: Oxford University Press.
13. Jenkins, J. (2006). Current perspectives on teaching World Englishes and English as a lingua franca. TESOL Quarterly, 40(1), 157–181. https://doi.org/10.2307/40264515
14. Jenkins, J. (2009). World Englishes: A resource book for students. Routledge.
15. Kang, O., Thomson, R. I. and Murphy, J. (2022). Automatic speech recognition for assessing pronunciation. Language Testing, 39(4), 529–550.
16. Kartal, G. and Korucu-Kış, S. (2020). The use of Twitter and YouGlish as two complementary digital tools in learning pronunciation. Education and Information Technologies, 25, 193–221. https://doi.org/10.1007/s10639-019-09970-8
17. Kartushina, N. and Martin, C. D. (2019). The impact of feedback on second-language pronunciation learning with ASR. Frontiers in Psychology, 10, 1326.
18. Levis, J. M., Sonsaat, S., Link, S. and Barriuso, T. (2016). ASR-based pronunciation training. Studies in Second Language Learning and Teaching, 6(3), 431–451.
19. Liakin, D., Cardoso, W. and Liakina, N. (2017). L2 pronunciation training through mobile apps. Computer Assisted Language Learning, 30(7), 691–709.
20. Möller, S., Engelke, U. and Möller, C. (2021). Automatic assessment of intelligibility in non-native speech. Speech Communication, 132, 27–38.
21. Munro, M. J. and Derwing, T. M. (1995a). 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
22. Munro, M. J. and Derwing, T. M. (1995b). Processing time, accent, and comprehensibility in the perception of native and foreign-accented speech. Language and Speech, 38(3), 289–306.
23. Nelson, C. (1995). Intelligibility and world Englishes in the classroom. World Englishes, 14(2), 273–279.
24. Pickering, L. (2006). Current research on intelligibility in World Englishes. World Englishes, 25(1), 11–16.
25. Ramjattan, V. (2023). The social politics of accent in English language workplaces. Journal of Sociolinguistics, 27(2), 202–217.
26. Saito, K., Suzukida, Y. and Sun, H. (2023). Quantifying L2 pronunciation improvement through ASR technology. Applied Linguistics, 44(1), 1–24.
27. Segalowitz, N. (2010). Cognitive bases of second language fluency. Routledge.
28. Sertdemir, M., Aydemir, E. and Koç, D. (2025). Pronunciation instruction in Turkish ELT curricula: An evaluation. ELT Research Journal, 14(2), 89–107.
29. Smith, L. (1976). The spread of English and issues of intelligibility. World Language English, 5(1), 45–56.
30. Trofimovich, P. and Gatbonton, E. (2006). Repetition and focus on form in processing L2 Spanish words: Implications for pronunciation instruction. The Modern Language Journal, 90(4), 519–535. https://doi.org/10.1111/j.1540-4781.2006.00464.x
31. Yalçınkaya, G. D. and Çalışkan, N. (2022). Ortaokul Düzeyinde Yabancı Dil Ağırlıklı Programların Öğrenci Görüşlerine Göre Değerlendirilmesi. Ahi Evran Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 8(2), 365-378.