Classification of Audio Data Using a Centroid Neural Network

Abstract

The automatic classification of audio data is an effective way to organize a large-scale audio data files. In this paper, an automatic content-based audio classification model using Centroid Neural Networks (CNN) with a Divergence Measure is proposed. The Divergence-based Centroid Neural Network (DCNN) algorithm, which employs the divergence measure as its distance measure, is used for clustering of Gaussian Probability Distribution Function (GPDF) data. In comparison with other conventional algorithms, the D-CNN designed for probability data has the robustness advantages of utilizing a audio data representation method in which each audio data is represented by a Gaussian distribution feature vector. Experiments and results show that the proposed classification model very compatible classification accuracy with classical models employing the conventional k-means and CNN algorithms.