Role of features and classifiers on accuracy of identification of musical instruments

Abstract

Listen

Translate article

Selection of effective feature set and proper classifier is a challenging task in problems where machine learning techniques are used. In automatic identification of musical instruments also it is very crucial to find the right set of features and accurate classifier. In this paper, we have discussed the role of various features with different classifiers on automatic identification of musical instruments. Piano, flute, trumpet, guitar, xylophone and violin are identified using various features and classifiers. Spectral features like spectral centroid, spectral slope, spectral spread, spectral kurtosis, spectral skewness and spectral roll-off are used along with zero crossing rate, autocorrelation and Mel Frequency Cepstral Coefficients (MFCC) for this purpose. The dependence of instrument identification accuracy on these features is studied for different classifiers. Decision trees, Naive Bayes classifier, k nearest neighbour classifier, multilayer perceptron, Sequential Minimal Optimization Algorithm (SMO) and multi class classifier (metaclassifier) are used. We have obtained improved accuracy by proper selection of these features and classifier. The analysis also confirms the selection of features and classifiers as the results are better.