Development of a Reference Platform for Generic Audio Classification (original) (raw)

Specific sounds such as applause, laugh, music, environmental noise, etc. are very helpful to understand high level semantic of the multimedia content. The detection of such key sounds is one of the challenges in intelligent management of multimedia information and content understanding. In this paper, we report a progress in development of the reference content-based audio classification algorithm that is based on a conventional and widely accepted approach, namely signal parameterization by MFCC followed GMM classification. The developed labelled audio database and this conventional classification model should serve as a reference and test platform for evaluation of novel, alternative or more advanced methods of audio content analysis.