Application of Bhattacharyya kernel-based Centroid Neural Network to the classification of audio signals
Jaeyoung Kim, Dong-Chul Park · 2009
A novel approach for the classification of audio signals using centroid neural network with Bhattacharyya kernel (CNN/BK) is evaluated and reported in this paper. The classifier is based on centroid neural network (CNN) and also exploits advantages of the kernel method for mapping input data into a higher dimensional feature space. Extensive experiments and results on a set of audio data demonstrate that the classification scheme based on CNN/BK outperforms CNN and self-organizing map (SOM) that utilize Euclidean distance for their distance measure in terms of classification accuracy.