SUN’IY INTELLEKTNING TABIIY TILNI QAYTA ISHLASHDA ASR TEXNOLOGIYALARI. O‘ZBEK TILI UCHUN ASR NI QO‘LLASHDAGI KAMCHILIKLAR
Keywords:
ASR, Sun’iy intellekt, O‘zbek tili, Kam resursli tillarAbstract
Ushbu ishda sun’iy intellektga asoslangan avtomatik nutqni tanish (ASR) texnologiyalari va ularning o‘zbek tilida qo‘llanishdagi cheklovlar tahlil qilindi. Tadqiqotda an’anaviy va chuqur o‘rganishga asoslangan modellar kam resursli til sharoitida solishtirildi. O‘zbek tilining morfologik murakkabligi, dialektlar va dataset yetishmasligi tizim samaradorligiga ta’sir ko‘rsatadi. Kam resursli tillar uchun istiqbolli yondashuvlar sifatida transfer learning, multilingual modellar va subword/fonema asosidagi usullar tavsiya qilindi.
References
1. Besacier, L., Barnard, E., Karpov, A., & Schultz, T. (2014). Automatic speech recognition for under-resourced languages: A survey. Speech communication, 56, 85-100.
2. Ma, Z., Yang, G., Yang, Y., Gao, Z., Wang, J., Du, Z., ... & Chen, X. (2024). An embarrassingly simple approach for llm with strong asr capacity. arXiv preprint arXiv:2402.08846.
3. Oruh, J., Viriri, S., & Adegun, A. (2022). Long short-term memory recurrent neural network for automatic speech recognition. IEEE Access, 10, 30069-30079.
4. Mukhamadiyev, A., Khujayarov, I., Djuraev, O., & Cho, J. (2022). Automatic speech recognition method based on deep learning approaches for Uzbek language. Sensors, 22(10), 3683.
