NNET BASED AUDIO CONTENT CLASSIFICATION AND INDEXING SYSTEM

Rapid advancement in computers and internet technology has led large volume of multimedia files. The archiving and digitization of the old media contents also contributes to the growth of the digital library. The usefulness of these collections is largely dependent upon the availability, information retrieval, and search tools. Soundtracks are information-rich and there is a lot of related information can be extracted from them; that enabling metadata generation and semantic search. This paper proposes a machine learning system based on neural network; the system use set of audio features that belong to three different feature spaces as a training/testing features; this regime will presents a generic structure of a preprocessing stage for automated metadata generation.