Taxonomy of Music Genre Using Machine Intelligence from Feature Melting Technique

Music is an effectual therapy in our life that makes us calm, cheerful, and excited. Music genre classification (MGC) is essential for recommendation of music and information retrieval. In our proposed work, an effective automatic musical genre classification approach has been experimented with where different features and order are fused together to get a better progressive result than the existing method. Frame-wise extraction of time-domain features(Wavelet scattering, Zero Crossing Rate, energy) and frequency-domain features(Mel Frequency Cepstral Coefficient-MFCC, pitch, Linear Predictive Coefficient-LPC) is done here. After that, the mean value of each extracted feature is put in a vector and fed to the classifier. Two well-known machine learning (ML) algorithms, Support Vector Machine (SVM) and K-Nearest Neighbor (KNN) are used to classify the GTZAN dataset. The proposed method outperformed than the existing work.