JET_V3_N1_RP2
A Multi-Language System For Knowledge Extraction In E-Learning Videos
Aparesh Sood
Ankush Mittal
Divya Sarthi
Journal of Educational Technology
2230 - 7125
3
1
48
55
Filter, Filter Graph, Annotation, Captioning and Speech Synthesizer, COM (Component Object Model)
The existing multimedia software in E-Learning does not provide par excellence multimedia data service to the common user, hence E-Learning services are still short of intelligence and sophisticated end user tools for visualization and retrieval. An efficient approach to achieve the tasks such as, regional language narration, regional language captioning system and keywords based efficacious seek to save the bandwidth, is introduced in this paper. The goal is to reduce the language barrier and seeking time for E-Learning videos. The paper presents an innovative solution of E-Learning multimedia delivery package for client-server model.
The functioning of the software tool can be described in different modules. Initially the system integrates keywords enriched subtitle stream with the video file at the server side. At the client side, the algorithm parses the video file into different streams. The synchronized text stream is then transformed into the uncompressed video stream and later overlaid onto the primary video to reproduce regional language captioned video. The system also encompasses a text annotation pad with intention to facilitate the future comprehension. Moreover, the user can upload his notes on server to make it available publicly. Regional language narrator is one of the advanced features supported by the system.Component Object Model (COM) has been used extensively for extending the system to include multiple numbers of language translators and narrators at both the server as well as the client sides.
April - June 2006
Copyright & copy; 2006 i-manager publications. All rights reserved.
i-manager Publications
http://www.imanagerpublications.com/Article.aspx?ArticleId=1009