Generating MPEG 7 audio descriptor for content-based retrieval

Abstract

The problem of classification of continuous general data for content based retrieval and describe the scheme that able to classify the audio segments based on the MPEG-7 audio descriptors and description schemes that consist of tools for indexing audio media using probabilistic sound models. The descriptors provide containers for category labels as well as data structures for quantitative information about sound content. We describe the normative tools as well as informative methods for automatic description extraction.