Music Genre Classification using Deep Neural Networks

G. Jawaherlalnehru, Subbaiyan Jothilakshmi · Zenodo (CERN European Organization for Nuclear Research) · 2018

Music genres can be defined as categorical labels created by humans to identify or characterize the style of music. This work presents a comprehensive machine learning approach to the problem of automatic musical genre classification using the audio signal. The system is developed using a Deep Neural Network (DNN) to recognize the genres. Mel Frequency Cepstral Coefficients (MFCC) features are used to represent the music characteristics. The system is evaluated with MIR datasets. The proposed system observed higher classification accuracy of 97.8%.

Read the paper · More papers on PaperTik