This article analyzes the scientific basis for creating a continuous speech recognition system based on artificial intelligence for the Uzbek language. The study systematically summarizes the stages of corpus formation, data preprocessing, acoustic modeling, language model construction, decoding and results evaluation based on the primary sources under investigation. Comparative analysis, structural synthesis and interpretation of published results were used as a methodological basis. The studied literature shows that the quality of speech recognition in the Uzbek language is determined, first of all, by the quality and size of the corpus, the preprocessing discipline, hybrid deep learning architectures and language models adapted to the agglutinative nature of the Uzbek language. Based on these results, a six-stage architecture is proposed, consisting of corpus formation, preprocessing, character separation, acoustic modeling, language model construction and decoding with error evaluation.
| Mualliflar | Arzikulov, Husan |
|---|---|
| Jurnal | Techscience.uz - техника фанлари долзарб масалалри |
| Nashriyot | Жиззах политехника институти |
| ISSN | 3030-3702, 3030-3702 |
| Nashr sanasi | 2026-03-25 |
| Jild | 4 |
| Son | 3 |
| Betlar | 25-31 |
| Til | Ingliz |
| Ilmiy soha | Texnika |
| DOI | 10.47390/ts-v4i3y2026n04 |
| Indeksga qo‘shilgan | 2026-08-26 |
DOI: 10.47390/ts-v4i3y2026n04 · Maqolaning asl sahifasi
artificial intelligence; Uzbek language; automatic speech recognition; speech corpus; acoustic model; language model; deep learning; CTC-attention; WER; CER., sun’iy intellekt; o‘zbek tili; avtomatik nutqni tanish; nutq korpusi; akustik model; til modeli; chuqur o‘rganish; CTC - diqqat; WER; CER.
| APA | Arzikulov, Husan (2026). CREATION OF ARTIFICIAL INTELLIGENCE-BASED CONTINUOUS SPEECH RECOGNITION SYSTEM FOR UZBEKISTAN: DESIGN OF CORPUS, ACOUSTIC MODEL AND LANGUAGE MODEL. Techscience.uz - техника фанлари долзарб масалалри, 4(3), 25-31. https://doi.org/10.47390/ts-v4i3y2026n04 |
|---|---|
| GOST (OAK) | Arzikulov, Husan CREATION OF ARTIFICIAL INTELLIGENCE-BASED CONTINUOUS SPEECH RECOGNITION SYSTEM FOR UZBEKISTAN: DESIGN OF CORPUS, ACOUSTIC MODEL AND LANGUAGE MODEL // Techscience.uz - техника фанлари долзарб масалалри. – 2026. – T. 4, № 3. – P. 25-31. – DOI: 10.47390/ts-v4i3y2026n04. |
| MLA | Arzikulov, Husan. “CREATION OF ARTIFICIAL INTELLIGENCE-BASED CONTINUOUS SPEECH RECOGNITION SYSTEM FOR UZBEKISTAN: DESIGN OF CORPUS, ACOUSTIC MODEL AND LANGUAGE MODEL.” Techscience.uz - техника фанлари долзарб масалалри, 4(3), 25-31, 2026. https://doi.org/10.47390/ts-v4i3y2026n04 |
| Chicago | Arzikulov, Husan. “CREATION OF ARTIFICIAL INTELLIGENCE-BASED CONTINUOUS SPEECH RECOGNITION SYSTEM FOR UZBEKISTAN: DESIGN OF CORPUS, ACOUSTIC MODEL AND LANGUAGE MODEL.” Techscience.uz - техника фанлари долзарб масалалри, 4(3), 25-31 (2026). https://doi.org/10.47390/ts-v4i3y2026n04 |
| Harvard | Arzikulov, Husan (2026) ‘CREATION OF ARTIFICIAL INTELLIGENCE-BASED CONTINUOUS SPEECH RECOGNITION SYSTEM FOR UZBEKISTAN: DESIGN OF CORPUS, ACOUSTIC MODEL AND LANGUAGE MODEL’, Techscience.uz - техника фанлари долзарб масалалри, 4(3), 25-31. https://doi.org/10.47390/ts-v4i3y2026n04 |
| BibTeX | @article{arzikulovhusan2026,
title = {CREATION OF ARTIFICIAL INTELLIGENCE-BASED CONTINUOUS SPEECH RECOGNITION SYSTEM FOR UZBEKISTAN: DESIGN OF CORPUS, ACOUSTIC MODEL AND LANGUAGE MODEL},
author = {Arzikulov, Husan},
journal = {Techscience.uz - техника фанлари долзарб масалалри},
year = {2026},
volume = {4},
number = {3},
pages = {25-31},
doi = {10.47390/ts-v4i3y2026n04},
url = {https://doi.org/10.47390/ts-v4i3y2026n04}
} |
Boshqa maqola uchun iqtibos tayyorlash
This article analyzes Coordinate Measuring Machines (CMMs), which serve as the primary tool for product quality control in modern industry, specifically in automotive manufacturing. The study highlights the limitations…
The paper analyzes mechanical and physical testing methods of polymer materials based on national standards of Uzbekistan and international ISO and ASTM standards. Testing methodologies are compared, and modern…
This paper presents a system for analyzing emergency medical calls using artificial intelligence technologies for dispatch services. The system is based on a Whisper-Small model fine-tuned on datasets FeruzaSpeech and…
This article addresses the development of a remote cardiovascular disease monitoring system integrated with Natural Language Processing (NLP) technologies. Based on a systematic literature review and comparative…
This article analyzes the prospects for applying artificial intelligence (AI) technologies to further develop the tax administration system in Uzbekistan. In the context of digitalization, it examines the possibilities…
This narrative review synthesizes 20 peer-reviewed and grey-literature sources (2020–March 2026) to chronicle multimodal AI’s evolution in vision assistance and neural restoration. From foundational vision-language…
Understanding the mechanisms governing groundwater level variations is of considerable scientific importance for analysing the formation and development of hydrogeological systems. The movement of groundwater represents…
The article analyzes the importance of foresight technology in probabilistic risk assessment within industrial and organizational systems. Foresight technology is considered a modern scientific and analytical approach…
This article presents a scientific and methodological analysis of improving the quality management methodology for textile products based on the international 4-point assessment system. The key criteria of the…
This paper analyzes the main sources of dust generation in industrial enterprises and the aerodynamic properties of dust particles. Dust formation is mainly associated with mechanical dispersion, physicochemical phase…
Techscience.uz - техника фанлари долзарб масалалри — barcha maqolalar · 2026-yil arxivi
The article examines the effective use of analytical methods in case analysis of systems whose mathematical models are represented by second-order nonlinear differential equations. Mathematical models of complex…
This article examines compression as a meaning-oriented strategy in sign language translation and interpreting. Compression is understood not as arbitrary shortening, but as the selective reformulation of a source…
This study investigates the impact of Edge Computing on bandwidth utilization in Internet of Things (IoT)–driven Nigerian telecom networks. The rapid growth of IoT devices has significantly increased data traffic…
This article analyzes the scientific, pedagogical, and methodological foundations for the effective integration of national upbringing factors with modern global competencies in the context of continuous education…
This article addresses the problem of improving an adaptive traffic signal control algorithm at urban intersections by taking into account the dynamic characteristics of traffic flow. Fixed-time control under conditions…
Maqolada paxta xomashyosini yirik iflosliklardan tozalash jarayonida arrali baraban va kolosnikli panjara o‘rtasidagi o‘zaro ta’sirni takomillashtirish masalasi ko‘rib chiqilgan. Mavjud tozalagichlarda qo‘llaniladigan…
Maqolada paxta xomashyosini yirik va mayda iflosliklardan tozalash samaradorligini oshirishga qaratilgan ilmiy tadqiqotlar tizimlashtirilib, konstruktiv va texnologik omillarning o‘zaro ta’siri qiyosiy tahlil qilindi…