Publication

Abstract : This paper introduces the Audio Feature Extraction for classifying the music based on Raga which plays a major role in Music Information Retrieval (MIR) systems. The backbone Indian Classical Music is its Raga. A Raga is a particular blend of notes which follows specific laws. The existing MIR systems and audio search engines concentrate on content based audio mining and also the searches are made by Meta Data which needs human effort for tagging. The existing MIR systems also do not concentrate on Ragas . In this paper, we propose how the frequency can be used to determine a raga by using Linear Predictive Coding(LPC). We also propose a method to identify the Raga of the input audio clip using Latent Semantic Indexing(LSI).