Asosiy kontentga oʻtish
AkademIndex

Mahsulotlar

Ishlab chiquvchilar uchun

AkademBasetez oradaEkotizim uchun ochiq API
Lotin
Maqola

AI-Based Speech Recognition Systems for EV Technician Education in Charging Infrastructure Operations

Наргиза Ахмедовна ТураповаHigher School of Japanese Studies, PhD, Tashkent State University of Oriental StudiesSultanbek BoltaboevOriental University,Department of Oriental LanguagesZohid MatyakubovUrgench State University,Department of English and Literature,Urgench,Uzbekistan,220100Madina AbdullayevaNamangan state institute of foreign languages,Namangan,Uzbekistan,160123Barno ShamsimetovaInternational Islamic Academy of UzbekistanGulnora UmarbekovaAlfraganus University,Department of Russian Language and Literature
2025
ABI

Annotatsiya

The rapid expansion of electric vehicle (EV) adoption has created a pressing need for skilled technicians capable of managing and maintaining complex charging infrastructure systems. Traditional training methods for EV technicians often rely on textual manuals, in-person demonstrations, and unstructured learning materials, which limit the ability of learners to efficiently acquire operational knowledge and quickly respond to technical issues. To address these challenges, this paper proposes an AI-Based Speech Recognition System for EV Technician Education in Charging Infrastructure Operations (AI-SR-TEC), which leverages advanced deep learning and natural language processing techniques to transcribe, interpret, and provide interactive feedback on spoken instructions and technician queries. AI-SR-TEC integrates automatic speech recognition, domain-specific terminology adaptation, and real-time corrective guidance to enhance the training experience, enabling technicians to practice hands-on procedures with voice-guided support. Experimental evaluation on a curated dataset of EV charging operation dialogues demonstrated that AI-SR-TEC achieved a word recognition accuracy of 94%, improved task completion efficiency by 31%, and enhanced learner comprehension scores by 28% compared to conventional lecture-based training approaches. The system also facilitated adaptive learning by identifying recurring errors and providing targeted feedback. In conclusion, AI-SR-TEC offers a scalable and intelligent solution for advancing EV technician education, bridging the gap between theoretical instruction and practical operational proficiency, and promoting efficient skill acquisition in EV charging infrastructure management.

Mavzular

Identifikatorlar

Iqtiboslar va manbalar

Koʻrsatkichlar — AkademScholar · Tez orada