Automatic Music Mood Classification of Hindi Songs
Braja Gopal Patra, Dipankar Das, Sivaji Bandyopadhyay · 2013
The popularity of internet, downloading and purchasing music from online music shops are growing dramatically. As an intimate relationship presents between music and human emotions, we often choose to listen a song that suits our mood at that instant. Thus, the automatic methods are needed to classify music by moods even from the uploaded music files in social networks. However, several studies on Music Information Retrieval (MIR) have been carried out in recent decades. In the present task, we have built a system for classifying moods of Hindi songs using different audio related features like rhythm, timber and intensity. Our dataset is composed of 230 Hindi music clips of 30 seconds that consist of five mood clusters. We have achieved an average accuracy of 51.56 % for music mood classification on the above data. 1