Abstract—Nowadays labelling video data and analysis the resource information from video is very popular but it is difficult for storage and time consuming. Instead of video, audio is pretty one and, audio signal processing and audio annotation is at the heart of highlighting, recording, storing and transferring. The big data processing and training is challenging in research work and how to reduce data size and speedy highlight is the majority job in real world. In this proposed system, the process of audio annotation is focused on boxing video to entertain without time exhausting. This system is intended to provide boxing lover to highlight, review and replay their desired part by removing unwanted video parts. The decision tree is used for classifying audio and support vector machine is combined to enhance the classification accuracy and to promote the weakness of decision tree.
 

Index Terms—signal processing, support vector machine, decision tree

Cite: K. Zin Lin and Khin Htar Nwe, "Audio Annotation on Myanmar Traditional Boxing Video by Enhancing DT," Journal of Advances in Information Technology, Vol. 12, No. 2, pp. 107-112, May 2021. doi: 10.12720/jait.12.2.107-112

Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.