Audio events detection based highlights extraction from baseball, golf and soccer games in a unified framework

Ziyou Xiong, Regunathan Radhakrishnan, Ajay Divakaran, Thomas S Huang

Research output: Contribution to journalArticlepeer-review

Abstract

We developed a unified framework to extract highlights from three sports: baseball, golf and soccer by detecting some of the common audio events that are directly indicative of highlights. We used MPEG-7 audio features and entropic prior Hidden Markov Models(HMM) as the audio features and classifier respectively to recognize these common audio events. Together with pre- and post-processing techniques using general sports knowledge, we have been able to generate promising results dealing with the audio track that is dominated by audio mixtures and noisy background.

Original languageEnglish (US)
Pages (from-to)632-635
Number of pages4
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume5
StatePublished - 2003

Keywords

  • Audio Features
  • HMM
  • Sport Highlights
  • Unified Framework

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Audio events detection based highlights extraction from baseball, golf and soccer games in a unified framework'. Together they form a unique fingerprint.

Cite this