Event detection in short duration audio using Gaussian Mixture Model and Random Forest Classifier

Abstract

The amount of online multimedia files is increasing day by day with the ever increasing popularity of video sharing websites. This has led to a huge interest in content analysis of multimedia files. Audio being a major component of multimedia has the potential to help analyze different events occurring in a multimedia recording. In this paper we present an audio event detection mechanism based on Gaussian Mixture Model (GMM) and Random Forest Classifier. Experiments show that our proposed mechanism shows significant improvement in detection of specifically finer audio events in short duration recordings.