FONETIK-PROSODIK XATOLAR ASOSIDA AVTOMATIK TAVSIYALAR SHAKLLANTIRUVCHI GAPIRISH MODULI
Article Sidebar
Main Article Content
Abstract
Maqolada xorijiy og‘zaki nutqda aniqlangan fonetik va prosodik xatolarni pedagogik jihatdan amaliy tavsiyalarga aylantiruvchi gapirish moduli taklif etilgan. Modul majburiy fonetik tekislash, MDD va prosodik diagnostika natijalarini fonema–bo‘g‘in–so‘z–jumla darajasidagi yagona xato profilida birlashtiradi. Har bir nomzod tavsiya xatoning og‘irligi, takrorlanishi, aniqlash ishonchliligi, kutilgan tuzatish foydasi, kognitiv yuklamasi va prerequisite holati bo‘yicha baholanadi. Xavfsiz Top-3 selektor bir turdagi tavsiyaning ortiqcha takrorlanishini cheklaydi, past ishonchli dalilni foydalanuvchiga chiqarmaydi va qayta yozish yoki ekspert ko‘rigiga yo‘naltiradi. 180 virtual profil asosidagi deterministik simulyatsiyada model Precision@3=0,659, nDCG@3=0,912, oracle foyda qamrovi=0,922 va ishonchli tavsiya ulushi=0,969 natijalarini ko‘rsatdi. Tajriba real respondent yoki pedagogik samaradorlik natijasi emas; algoritm mexanizmini tekshirish uchun mo‘ljallangan.
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
How to Cite
References
El Kheir Y., Ali A., Chowdhury S.A. Automatic Pronunciation Assessment — A Review. Findings of EMNLP 2023. P. 8304–8324. DOI: 10.18653/v1/2023.findings-emnlp.557.
Witt S.M., Young S.J. Phone-Level Pronunciation Scoring and Assessment for Interactive Language Learning. Speech Communication. 2000;30(2–3):95–108. DOI: 10.1016/S0167-6393(99)00044-7.
Ryu H., Kim S., Chung M. A Joint Model for Pronunciation Assessment and Mispronunciation Detection and Diagnosis with Multi-Task Learning. Interspeech 2023. P. 959–963. DOI: 10.21437/Interspeech.2023-337.
Chao F.-A., Chen B. Towards Efficient and Multifaceted Computer-Assisted Pronunciation Training Leveraging Hierarchical Selective State Space Model and Decoupled Cross-Entropy Loss. NAACL 2025. P. 1947–1961. DOI: 10.18653/v1/2025.naacl-long.98.
Yang T.-H., He Y.-Y., Chen B. JCAPT: A Joint Modeling Approach for CAPT. SLaTE 2025. P. 96–100. DOI: 10.21437/SLaTE.2025-20.
Yan B.-C., Li J.-T., Wang Y.-C., et al. An Effective Pronunciation Assessment Approach Leveraging Hierarchical Transformers and Pre-Training Strategies. ACL 2024. P. 1737–1747. DOI: 10.18653/v1/2024.acl-long.95.
Chao F.-A., Lo T.-H., Wu T.-I., Sung Y.-T., Chen B. A Hierarchical ContextAware Modeling Approach for Multi-Aspect and Multi-Granular Pronunciation Assessment. Interspeech 2023. P. 974–978. DOI: 10.21437/Interspeech.2023-550.
Pei H.-C., Fang H., Luo X., Xu X.-S. Gradformer: A Framework for MultiAspect Multi-Granularity Pronunciation Assessment. IEEE/ACM TASLP. 2024;32:554–563. DOI: 10.1109/TASLP.2023.3335807.
Gong Y., Chen Z., Chu I.-H., Chang P., Glass J. Transformer-Based MultiAspect Multi-Granularity Non-Native English Speaker Pronunciation Assessment. ICASSP 2022. P. 7262–7266. DOI: 10.1109/ICASSP43922.2022.9746743.
Wei X., Dong W., Cucchiarini C., van Hout R., Strik H. Leveraging Articulatory Information to Enhance End-to-End Models for L2 Mispronunciation Detection and Diagnosis. SLaTE 2025. P. 76–80. DOI: 10.21437/SLaTE.2025-16.
Wei X., Cucchiarini C., van Hout R., Strik H. Articulatory-Enhanced Mispronunciation Detection and Diagnosis Models: A Multi-Dimensional Error Analysis. SLaTE 2025. P. 31–35. DOI: 10.21437/SLaTE.2025-7.
Bang J., Kang S., Lee G.G. An Automatic Feedback System for English Speaking Integrating Pronunciation and Prosody Assessments. SLaTE 2013. P. 83– 89. DOI: 10.21437/SLaTE.2013-14.
Dong W., van Hout R., Cucchiarini C., Strik H. L2 Prosody Assessment by Combining Acoustic and Neural Model Features. Speech Prosody 2024. P. 165–169. DOI: 10.21437/SpeechProsody.2024-34.
Dong W., Cucchiarini C., van Hout R., Strik H. Automatic Pronunciation Assessment for L2 English by Incorporating Suprasegmental Features and Weighted Loss Function. SLaTE 2025. P. 21–25. DOI: 10.21437/SLaTE.2025-5.
Fu K., Gao S., Shi S., Tian X., Li W., Ma Z. Phonetic and Prosody-Aware SelfSupervised Learning Approach for Non-Native Fluency Scoring. Interspeech 2023. P. 949–953. DOI: 10.21437/Interspeech.2023-587.
McAuliffe M., Socolof M., Mihuc S., Wagner M., Sonderegger M. Montreal Forced Aligner: Trainable Text-Speech Alignment Using Kaldi. Interspeech 2017. P. 498–502. DOI: 10.21437/Interspeech.2017-1386.
Lee A., Glass J. Mispronunciation Detection without Nonnative Training Data. Interspeech 2015. P. 643–647. DOI: 10.21437/Interspeech.2015-231.
Mathad V.C., Mahr T.J., Scherer N., et al. The Impact of Forced-Alignment Errors on Automatic Pronunciation Evaluation. Interspeech 2021. P. 1922–1926. DOI: 10.21437/Interspeech.2021-1403.
Qian M., et al. PTeacher: A Computer-Aided Personalized Pronunciation Training System with Exaggerated Audio-Visual Corrective Feedback. arXiv:2105.05182, 2021. DOI: 10.48550/arXiv.2105.05182.
Chen Y.-W., Yu Z., Hirschberg J. MultiPA: A Multi-Task Speech Pronunciation Assessment Model for Open Response Scenarios. Interspeech 2024.
Yan B.-C., Wang H.-W., Chao F.-A., et al. HiPPO: Exploring a Novel Hierarchical Pronunciation Assessment Approach for Spoken Languages. IJCNLPAACL 2025. P. 810–823. DOI: 10.18653/v1/2025.ijcnlp-long.45.
Lin B., Wang L., Feng X., Zhang J. Automatic Scoring at Multi-Granularity for L2 Pronunciation. Interspeech 2020. P. 3022–3026. DOI: 10.21437/Interspeech.2020-1282.
Zhang J., Zhang Z., Wang Y., et al. speechocean762: An Open-Source NonNative English Speech Corpus for Pronunciation Assessment. Interspeech 2021. P. 3710–3714. DOI: 10.21437/Interspeech.2021-1259.
Baevski A., Zhou H., Mohamed A., Auli M. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. NeurIPS. 2020;33:12449– 12460. DOI: 10.48550/arXiv.2006.11477.
Hsu W.-N., Bolte B., Tsai Y.-H.H., et al. HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units. IEEE/ACM TASLP. 2021;29:3451–3460. DOI: 10.1109/TASLP.2021.3122291.
Chen S., Wang C., Chen Z., et al. WavLM: Large-Scale Self-Supervised PreTraining for Full Stack Speech Processing. IEEE JSTSP. 2022;16(6):1505–1518. DOI: 10.1109/JSTSP.2022.3188113.
Eyben F., Scherer K.R., Schuller B.W., et al. The Geneva Minimalistic Acoustic Parameter Set (GeMAPS). IEEE Transactions on Affective Computing. 2016;7(2):190–202. DOI: 10.1109/TAFFC.2015.2457417.
de Jong N.H., Wempe T. Praat Script to Detect Syllable Nuclei and Measure Speech Rate Automatically. Behavior Research Methods. 2009;41(2):385–390. DOI: 10.3758/BRM.41.2.385.
Koenecke A., Nam A., Lake E., et al. Racial Disparities in Automated Speech Recognition. PNAS. 2020;117(14):7684–7689. DOI: 10.1073/pnas.1915768117. ISO/IEC 25010:2023. Systems and Software Engineering — Systems and Software Quality Requirements and Evaluation (SQuaRE) — Product Quality Model. Geneva: ISO, 2023.