"RBFNN and AANN based Speech/music Classification using PNCC"

Authors

Dr. R. Thiruvengatanadhan (Assistant Professor)
Annamlai University, Annamalainagar, Tamilnadu, India.

Abstract

Audio classification serves as the fundamental step towards the rapid growth in audio data volume. Automatic audio classification is very useful in audio indexing; In this work a speech/music discrimination system is developed which utilizes the Power Normalized Cepstral Coefficients (PNCC) as the acoustic feature. The analysis is done on radial basis function neural network (RBFNN) and Autoassociative Neural Network (AANN) then a conclusion is formed on the basis of their performance and efficiency.