STM Journals Peer-reviewed research from Consortium e-Learning Network

Journal of Artificial Intelligence Research & Advances Review Article

Transcript Summarizer of YouTube Videos Using Deep Learning

  1. Jayesh Chavan Department of Electronics and Telecommunication, Smt. Kashibai Navale College of Engineering, Savitribai Phule Pune University, Pune
  2. Smita Palnitkar Department of Electronics and Telecommunication, Smt. Kashibai Navale College of Engineering, Savitribai Phule Pune University, Pune
  3. Ajinkya Kaje Department of Electronics and Telecommunication, Smt. Kashibai Navale College of Engineering, Savitribai Phule Pune University, Pune
  4. Chaitanya Bhopnikar Department of Electronics and Telecommunication, Smt. Kashibai Navale College of Engineering, Savitribai Phule Pune University, Pune

Abstract

Transcriber Sum is a deep learning-based YouTube transcript summarization tool. It employs advanced machine learning techniques to automatically generate concise summaries of YouTube video transcripts, enabling users to quickly grasp the key content and insights of videos without the need to watch or read the entire transcript. This Transcriber Sum addresses the challenge of providing users with concise and informative summaries of video content by harnessing the power of deep learning techniques. The objectives encompass the creation of advanced models for natural language processing and video content analysis, building a robust framework for processing and summarizing video transcripts, collecting and annotating a diverse dataset of YouTube video transcripts, implementing data preprocessing and augmentation techniques, training and evaluating the model’s performance, developing a user- friendly application for real-time transcript summarization, and continuously refining the model based on user feedback. The methodology involves developing deep learning models for natural language understanding, utilizing advanced video content analysis techniques, and seamlessly integrating these components into an application for effortless YouTube transcript summarization. Performance evaluation is conducted through a combination of simulation using synthetic data and real-world testing with a wide range of YouTube video transcripts. Transcriber Sum aims to empower users with a time-efficient and informative tool for quickly summarizing the wealth of content available on YouTube, ultimately enhancing the overall viewing experience and accessibility of valuable information in the digital age.

Keywords

References (10)

  1. P I, D NR, A T, M MT, S MK, A.S N, et al. Video Transcript Summarizer. E3S Web of Conferences. 2023;399:04015. doi:10.1051/e3sconf/202339904015
  2. Dharmapuri S, Desu S, Alladi K, Gummadi H, Gupta H, Shareef SNM. An Automated Framework for Summarizing YouTube Videos Using NLP. E3S Web of Conferences. 2023;430:01056. doi:10.1051/e3sconf/202343001056
  3. Albeer RA, AL-Shahad HF, Aleqabie HJ, Al-shakarchy ND. Automatic summarization of YouTube video transcription text using term frequency-inverse document frequency. Indonesian Journal of Electrical Engineering and Computer Science. 2022;26(3):1512. doi:10.11591/ijeecs.v26.i3.pp1512-1519
  4. Devi S, Nadar R, Nichat T, Lucas A. Abstractive summarizer for YouTube videos. In: International Conference on Applications of Machine Intelligence and Data Analytics (ICAMIDA 2022). Atlantis Press; 2023. p. 431–8.
  5. P I, D NR, A T, M MT, S MK, A.S N, et al. Video Transcript Summarizer. E3S Web of Conferences. 2023;399:04015. doi:10.1051/e3sconf/202339904015
  6. Li H, Zhu J, Ma C, Zhang J, Zong C. Read, Watch, Listen, and Summarize: Multi-Modal Summarization for Asynchronous Text, Image, Audio and Video. IEEE Transactions on Knowledge and Data Engineering. 2019;31(5):996-1009. doi:10.1109/tkde.2018.2848260
  7. Emad A, Bassel F, Refaat M, Abdelhamed M, Shorim N, AbdelRaouf A. Automatic video summarization with timestamps using natural language processing text fusion. In: 2021 IEEE 11th Annual Computing and Communication Workshop and Conference (CCWC). IEEE Publications; 2021. p. 0060–6.
  8. Wolf T, Debut L, Sanh V, Chaumond J, Delangue C, Moi A, et al. Transformers: State-of-the-Art Natural Language Processing. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 2020:38-45. doi:10.18653/v1/2020.emnlp-demos.6
  9. Jain A, Department of Computer Engineering, SVKMs NMIMS MPSTME Shirpur, Maharashtra, India, Kulkarni G, Department of Computer Engineering, SVKMs NMIMS MPSTME Shirpur, Maharashtra, India, Shah V, Department of Computer Engineering, SVKMs NMIMS MPSTME Shirpur, Maharashtra, India. Natural Language Processing. International Journal of Computer Sciences and Engineering. 2018;6(1):161-167. doi:10.26438/ijcse/v6i1.161167
  10. Joseph SR, Hlomani H, Letsholo K, Kaniwa F, Sedimo K. Natural language processing: A review. Int J Res Eng Appl Sci. 2016;6:207–10.
Support