COMPARISON OF ENHANCED SCHEMES FOR AUDIO CLASSIFICATION
No Thumbnail Available
Date
2013
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
In the modem era of communication, audio plays an important role in understanding a digital media. Due to the rise of
economical audio capturing devices, the amount of audio data available both online and offline is enormous and techniques that
can automatically classify and retrieve these audio data is an immediate need. An automatic content based audio classification and
retrieval system consists of three modules namely, feature extraction, classification and retrieval. This paper presents a
comparative smdy of two algorithms that performs these three steps in different manners. The performance of the selected systems
are analyzed while using four different features (acoustic, percepmal, mel-frequency cepstral coefficients (MFCC) and a
''"mbination of percepmal and MFCC) and four classifiers that enlianced Support Vector Machine (SVM) and Centroid Neural
itwork (CNN) along with its base versions, SVM and CNN. Experimental results showed that the enhanced SVM algorithm
when using the combined feature vector produced improved accinacy and reduced error rate.