Audio Retrieval Using Multiple Feature Vectors

Content Based Audio Retrieval system is very helpful to facilitate users to find the target audio materials. Audio signals are classified into speech, music, several types of environmental sounds and silence based on audio content analysis. The extracted audio features include temporal curves of the average zero-crossing rate, the spectral Centroid, the spectral flux, as well as spectral roll-off of these curves. In this dissertation we have used the four features for extracting the audio from the database, use of this multiple features increase the accuracy of the audio file which we are retrieving from the audio database.