Classification of Music Signal in to Genre using Probability Distribution Estimation
This paper presents a method for classification of music signal in to their respective genres using probability distribution estimation approach. Genre hierarchies are used to build large collections of music data available on the internet. The task of musical genre classification is performed manually by human experts. Different popular probability distributions are taken into consideration for this task. The processing is done in both time as well as frequency domain. MFCC coefficients are used as a basis to apply distribution estimation. Extensive simulation results on different datasets are provided to demonstrate the usefulness and simplicity of the presented algorithm.
Keywords - Genre, Music Classification, Kurtosis, Probability Distribution Estimation.