Genre-Ation: A Music Genre Identification Application

Abstract

In this paper we present a novel and faster approach to identify songs by genre. Our application, Genre-Ation, converts the audio signals to spectrograms and waveforms and uses thresholding for feature extraction. In addition, we propose a user-friendly web interface for this application and we evaluate it through a usability testing. Experiments suggested that Genre-Ation outperforms the existing music applications in terms of creating accurate genre based playlist due to the fact that our application is attuned with songs without metadata.