Genres Classification of Popular Songs Listening by Using Keras

Abstract

Listening to the music affects the brain in ways which might help to promote the human health and arrange various diseases symptoms. Music is a phenomenon that is intertwined at every stage of human life. In the modern era music is formed by the combination of an incredible number of genres, some of which are contemporary, and some come from the past. The music genre represents a collection of musical works that develop according to a certain shape, expression and technique. The music genre of interest varies from person to person in society. Most listeners today do not know what kind of music they listen to. In this study, sound features were extracted from music data and the Keras model was trained using these features. The correct classification rate of a music genre of the trained model was determined as 71.66%. Mel Frequency Cepstral Coefficients (MFCC), Mel Spectrogram, Chroma Vector and Tonnetz methods in the Librosa library were used to extract sound properties from music data. Using the features calculated by the Librosa library, the most listened songs with Shazam in Türkiye were classified in with TensorFlow/Keras. Many methods can be used in classification. It is unclear which method the researchers should prefer. With this study, researchers will know classification with Keras, researchers who do not know about music will know music and know the genre of newly released songs.