Corpus-based discourse analysis: Automatic Speech Recognition (ASR) technologies and spoken corpus collection

Nargiza Asrorova

doi:10.47689/2181-3701-vol3-iss4-pp1-8

Nargiza Asrorova Doktorant, O‘zbekiston davlat jahon tillari universiteti, O‘qituvchi, TIFT Universiteti

DOI

https://doi.org/10.47689/2181-3701-vol3-iss4-pp1-8

Kalit so‘zlar

Avtomatik nutqni aniqlash (ASR) , nutq transkripsiyasi , korpus , og‘zaki diskurs tahlili , ikkinchi tilni o‘zlashtirish

Annotasiya

Ushbu tadqiqot Avtomatik nutqni aniqlash (ASR) texnologiyalarining ingliz tilini ikkinchi til sifatida (L2) o‘rganuvchilarning og‘zaki korpuslarini yig‘ish va tahlil qilish jarayoniga integratsiyasini o‘rganadi. Turli metodlarni aralashtirish usulida olib borilgan mazkur tadqiqot ishida Whisper va BERT asosidagi modellar misolida ASR tizimlarining aniq transkripsiyalar yaratish va ikkinchi til o‘zlashtirish jarayonini oshirishdagi samaradorligi baholandi. Miqdoriy natijalar transkripsiya yuqori aniqlikda ekanligini ko‘rsatdi, tavsifiy jihatdan esa ASR ga asoslangan fikr-mulohazalar (feedback) talabalar faolligining, hamda talaffuz va og‘zaki nutq ko‘nikmalarining sezilarli darajada yaxshilanishiga olib kelishini aniqladi. Texnologiyaning kamchilik tomonlari, ma’lumotlar maxfiyligi hamda fikr-mulohaza mexanizmlari bilan bog‘liq axloqiy masalalar ham tadqiqot doirasida o‘rganib chiqildi. Tadqiqot natijalari ASR texnologiyalarining til ta’limini tubdan o‘zgartirish salohiyatiga ega ekanligini tasdiqladi, ya’ni mazkur texnologiya o‘quvchilarni real vaqtda baholash va individuallashtirilgan fikr-mulohazalar (feedback) taqdim etish imkonini berib, til o‘rganuvchilarning har qanday toifa guruhlari uchun qo‘llanilishi mumkin deb topildi.

Bibliografik manbalar

Nakamura, S., Spring, R., & Sakurai, S. (2024). The impact of ASR-based interactive video activities on speaking skills: Japanese EFL learners’ perceptions. The Electronic Journal for English as a Second Language, 27(4). https://doi.org/10.55593/ej.27108a5

Gladia. (2023, December 19). A review of the best ASR engines and the models powering them in 2024. Gladia Blog. https://www.gladia.io/blog/a-review-of-the-best-asr-engines-and-the-models-powering-them-in-2024

Michot, J., Hürlimann, M., Deriu, J., Sauer, L., Mlynchyk, K., & Cieliebak, M. (2024). Error-preserving automatic speech recognition of young English learners’ language. Beta archives, https://arxiv.org/html/2406.03235v1

Qian, Z., Xiao, K., & Yu, C. (2023). A survey of technologies for automatic dysarthric speech recognition. Journal of Audio, Speech, and Music Processing, 2023(48). https://doi.org/10.1186/s13636-023-00318-2

Bhatnagar, N. (2024 Deep dive into ASR systems. Medium. https://medium.com/@captnitinbhatnagar/deep-dive-into-asr-systems-c571a576ff26

Sun, W. (2023). The impact of automatic speech recognition technology on second language pronunciation and speaking skills of EFL learners: A mixed methods investigation. Frontiers in Psychology, 14, Article 1210187. https://doi.org/10.3389/fpsyg.2023.1210187

Southwell, R., Pugh, S., Perkoff, E. M., Clevenger, C., Bush, J., Lieber, R., Ward, W., Foltz, P., & D’Mello, S. (2022). Challenges and feasibility of automatic speech recognition for modeling student collaborative discourse in classrooms. In Proceedings of the 15th International Conference on Educational Data Mining (EDM 2022) (pp. 342–353). https://educationaldatamining.org/edm2022/proceedings/2022.EDM-long-papers.26/index.html

Yuklashlar

PDF (English)

63 20

Nashr qilingan

2025-07-15

Qanday qilib iqtibos keltirish kerak

Asrorova, N. 2025. Korpusga asoslangan diskurs tahlili: Nutqni avtomatik aniqlash (ASR) dasturlari va og‘zaki nutq korpusini to‘plash. Xorijiy lingvistika va lingvodidaktika. 3, 4 (Jul. 2025), 1–8. DOI:https://doi.org/10.47689/2181-3701-vol3-iss4-pp1-8.