Automatic musical instrument classification using fractional fourier transform based- MFCC features and counter propagation neural network

摘要: This paper presents a novel feature extraction scheme for automatic classification of musical instruments using Fractional Fourier Transform (FrFT)-based Mel Frequency Cepstral Coefficient (MFCC) features. The classifier model the proposed system has been built Counter Propagation Neural Network (CPNN). discriminating capability features have maximized between-class and minimized within-class compared to other conventional Also, show significant improvement in accuracy robustness against Additive White Gaussian Noise (AWGN) McGill University Master Sample (MUMS) sound database used test performance system.