Paper Details

Text summarization aims to condense a source text into a shorter version. Automatic data summarization is partof data mining. The rapid growth in data transmission over the internet makes it necessary to create multi-modalsummarization (MMS) from asynchronous data (text, audio, and video). In thiswork, an MMS method combining the techniquesof natural language processing (NLP), speech processing, computer vision and advanced encryption standard (AES) encryptionis used to explore the rich information contained in multi-modal data, to improve the quality and security as well the key idea isto bridge and lessen the semantic gaps between multi-modal data. Video is basically composed of audio and visual (image).For audio, speech transcriptions are used. For visual information, the joint representations of image and text is studied usingan artificial neural network. Finally, all the multi-modal aspects are considered to generate a textual summary by maximizingthe salience, readability, non- redundancy. The summary so generated by text, audio or video is encrypted using AESencryption method (to make it secure) and stored on server, from where the user can retrieve it whenever required by providingthe decryption key.

Akshay Shegaonkar, Harshal, Anupama Anand Pande, Aishwarya Kamtikar, Mangesh Manake, “Secure Multi-Modal Summarization Using LexRank Algorithm”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 7, Issue 6, pp. 13-17, June 2020.