Music Genre Classification using MFCC, SVM and BPNN
Gursimran Kour, Neha Mehan · International Journal of Computer Applications · 2015
In the field of musical information retrieval, genre categorization is a complicated mission. MFCC is one of the feature extraction method use in classification of musical genre that is based on short speech signals. Searching and organizing are the main characteristics of the music genre classification system these days. This paper describes a new technique that uses support vector machines to classify songs based on features using MFCC, BPNN and SVM classifier does not classify songs based on the short signals. So these categories a number of acoustic features that include Melfrequency Cepstral coefficients are extracted to characterize the audio content. Support vector machines and BPNN classifies audio into their respective classes by learning from training data. The simulation is taken place in MATLAB by making experiments on different genres .The results obtained by this proposed technique are promising. General Terms Classification Algorithms, Pattern Recognition.