48 International Journal for Modern Trends in Science and Technology As per UGC guidelines an electronic bar code is provided to seure your paper International Journal for Modern Trends in Science and Technology, 7(01): 48-53, 2021 Copyright © 2021 International Journal for Modern Trends in Science and Technology ISSN: 2455-3778 online DOI: https://doi.org/10.46501/IJMTST070111 Available online at: http://www.ijmtst.com/vol7issue01.html Automatic Summarization of Cricket Highlights using Audio Processing Ritwik Baranwal Information Technology, Maharaja Agrasen Institute of Technology, New Delhi, India To Cite this Article Ritwik Baranwal, “Automatic Summarization of Cricket Highlights using Audio Processing”, International Journal for Modern Trends in Science and Technology, Vol. 07, Issue 01, January 2021, pp.- 48-53. Article Info Received on 22-November-2020, Revised on 18-December-2020, Accepted on 22-December-2020, Published on 29-December-2020. The problem of automatic excitement detection in cricket videos is considered and applied for highlight generation. This paper focuses on detecting exciting events in video using complementary information from the audio and video domains. First, a method of audio and video elements separation is proposed. Thereafter, the “level-of-excitement” is measured using features such as amplitude, and spectral center of gravity extracted from the commentators speech’s amplitude to decide the threshold. Our experiments using actual cricket videos show that these features are well correlated with human assessment of excitability. Finally, audio/video information is fused according to time-order scenes which has “excitability” in order to generate highlights of cricket. The techniques described in this paper are generic and applicable to a variety of topic and video/acoustic domains. KEYWORDS: Video Segmentation, Audio Chunks, Short Time Energy. I. INTRODUCTION This study focuses on the problem of identifying exciting-events in multimedia content. Our approach analyzes speech characteristics that identify islands (or “hot-spots”) of strong emotion. In general, the ability to automatically parse multimedia content and tag “interesting events” is important for many domains such as sports, security, movies/TV shows, broadcast news, etc. A number of technologies such as search, summation, and mash-ups, can utilize “hot-spot” information to enhance access to, as well as navigation of content. For example, emotional “hot-spots” within sports videos are very likely to be “exciting” and this information can be used to guide the process of automatically generating highlights. This constitutes the motivation for this work, where automatic highlights of cricket videos are generated using emotional “hot-spot” detection (or “exciting events” detection). Researchers have utilized audio and video streams to extract features that identify exciting plays in sports videos. Among video-based features, motion and density of cuts have been found to be useful for detection[1] . On the other hand, audio-based features have been derived from both speech (generally commentators) and background (generally audience), where audience-events like cheering/applause as well as the commentators speech characteristics have proven to be useful [2,3]. While video-based features tend to be more game-dependent, audio-based feature detecting exciting plays. Research in audio-based features have focused on emotion analysis of the commentator‟s speech and ABSTRACT