Raga Classification Based on Novel Method of Pitch Co-Occurrence

Abstract

Automatic identification of raga is a growing research area and has captured significant attention from movie making industry. It is the need of time to develop efficient tools for data mining the vast audio visual data on internet. In particular, to search for a specific raga. Applications of raga search are in musicological studies, similarity based search. Ascending and descending pattern of swaras is an important feature in the raga classification. Pitch tracks of swaras are obtained from raw audio recordings. This research has utilised the pattern developed due to co-occurrence of pitches of swaras for classification. This pattern gives a concise representation of the signal which contains time and frequency information of the raga. K Nearest Neighbour (KNN) has been used as the classifier.