An Advanced Approach to NLP Technique (Text ...

An Advanced Approach to NLP Technique (Text Summarization)

Author Name : Asst. Prof. Vijay Kumar, Mihir Binoli, Sarthak Tyagi, Shreya Soni

ABSTRACT This paper proposes a novel approach to multimodal summarization of YouTube videos and podcasts using deep learning. The proposed system integrates audio, text, and speaker information to generate informative and concise summaries tailored to individual user preferences. A multi-modal deep learning model leverages the power of the Llama 2 language model to capture the semantics of multimedia content and generate fluent and coherent summaries. The system is trained on a large dataset of YouTube videos and podcasts, enabling it to learn effective representations of different information modalities.