PMFCC Features for Music Classification Using the Modified KNN Algorithm

Abstract

From ancient period Music is a integral part of human life. People prefered to listen Music while relaxing. All over the world nowadays music is used as supporting medication for healing mental illness and many other diseases. The origin of Indian Music is Indian Classical Raga, having a melodious combination of Rhythm and notes. There are various users like music-composers, e-learners, music therapists are frequently retrieving Indian classical Raga based music. The vast retrieval of Raga based music made it necessary to classify Indian music on Raga. This paper proposes an a new algorithm to classify an Indian Music using Raga information which further will be useful for song recommendation, personalizing collection, and musicologists for various purpose.
 In this paper, the combined Pitch and MFCC based PMFCC features are extracted and processed by Modified K Nearest Neighbor algorithm. The performance of PMFCC and Pitch Class Distribution features is compared using traditional machine learning classification algorithms and Modified Variant K Nearest Neighbor (MVKNN). The PMFCC features outperformed with the Modified KNN algorithm. The accuracy of PMFCC features with Modified KNN algorithm is found 96.11% for our Our dataset and 93.65% for Compmusic standard dataset.