AI Powered Interactive Teaching Assistant

This paper presented IntelLearn, an AI-driven smart learning platform that integrates speech recognition, natural language processing, and large language models to automate educational content generation and enhance learning experiences. The system effectively transforms raw inputs such as lectures, videos, and multimedia into structured outputs including notes, quizzes, and presentations. The integration of a Retrieval-Augmented Generation (RAG) based AI tutor enables context-aware responses, improving accuracy and reducing reliance on generic knowledge. Additionally, multilingual support enhances accessibility, making the system suitable for diverse learning environments. Experimental evaluation demonstrates that the system achieves reliable performance in transcription accuracy, content generation, and response relevance while maintaining acceptable latency. The platform reduces manual effort, improves learning efficiency, and provides an interactive educational experience. Overall, IntelLearn highlights the potential of Artificial Intelligence in transforming traditional education into a more intelligent, scalable, and accessible system. Future enhancements may include model optimisation, offline capabilities, and personalised adaptive learning features.

[1] T. Brown et al., “Language Models are Few-Shot Learners,” Advances in Neural Information Processing Systems (NeurIPS), vol. 33, 2020. [2] A. Radford et al., “Whisper: Robust Speech Recognition via Large-Scale Weak Supervision,” OpenAI, 2022. [3] P. Lewis et al., “Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,” NeurIPS, 2020. [4] H. Touvron et al., “LLaMA: Open and Efficient Foundation Language Models,” Meta AI, 2023. [5] J. Devlin et al., “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” NAACL, 2019. [6] S. Ji et al., “Evaluating Large Language Models for NLP Tasks,” IEEE, 2023. [7] M. Tavallaee et al., “A Detailed Analysis of the KDD Cup 99 Dataset,” IEEE Symposium on Computational Intelligence, 2009. [8] I. Sharafaldin et al., “Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterisation,” ICISSP, 2018. [9] R. Vinayakumar et al., “Deep Learning Approach for Network Intrusion Detection,” IEEE Access, 2019. [10] H. Guo et al., “LogBERT: Log Anomaly Detection via BERT,” IEEE IJCNN, 2021.