Raga identification from Hindustani classical music signal using compositional properties

Classification of music signal is a fundamental step for organized archival of music collection and fast retrieval thereafter. For Indian classical music, raga is the basic melodic framework. Manual identification of raga demands high expertise which is not available easily. Thus an automated system for raga identification is of great importance. In this work, we have studied the basic properties of the ragas in North Indian (Hindusthani) classical music and designed the features to capture the same. Pitch based Swara (note) profile is formed. Occurrence and energy distribution of notes generated from the profile are used as features. Note sequence plays an important role in the raga composition. Proposed note co-occurrence matrix summarizes this aspect. An audio clip is represented by these features which have strong correlation with the properties of raga. Support vector machine is used for classification. Experiment is done with a diversified dataset. Performance of the proposed work is compared with two other systems. It is observed that proposed methodology performs better.

[1]  Chaitanya Mishra,et al.  TANSEN: A System for Automatic Raga Identification , 2003, IICAI.

[2]  Preeti Rao,et al.  Detection of Raga-characteristic phrases from Hindustani Classical Music Audio , 2012 .

[3]  Parag Chordia,et al.  Raag Recognition Using Pitch-Class and Pitch-Class Dyad Distributions , 2007, ISMIR.

[4]  Surendra Shetty,et al.  Raga Mining of Indian Music by Extracting Arohana-Avarohana Pattern , 2009 .

[5]  Xavier Serra,et al.  Rāga Recognition based on Pitch Distribution Methods , 2012 .

[6]  Bonnie C. Wade.  Chiz in Khyal: The Traditional Composition in the Improvised Performance , 1973 .

[7]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[8]  Meinard Müller,et al.  Chroma Toolbox: Matlab Implementations for Extracting Variants of Chroma-Based Audio Features , 2011, ISMIR.

[9]  R. Sridhar.  Raga Identification of Carnatic music for Music Information Retrieval , 2009 .

[10]  Meinard Müller,et al.  Audio Matching via Chroma-Based Statistical Features , 2005, ISMIR.

[11]  Krishna Pawan Kumar,et al.  Raaga identification using clustering algorithm , 2016, 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT).

[12]  J. Platt.  Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines , 1998 .

[13]  Hema A. Murthy,et al.  Classification of Melodic Motifs in Raga Music with Time-series Matching , 2014 .

[14]  C. V. Jawahar,et al.  Identifying Ragas in Indian Music , 2014, 2014 22nd International Conference on Pattern Recognition.

[15]  Richard Widdess,et al.  Dhrupad: Tradition and Performance in Indian Music , 2004 .

[16]  Emilia Gómez,et al.  Melody Extraction From Polyphonic Music Signals Using Pitch Contour Characteristics , 2012, IEEE Transactions on Audio, Speech, and Language Processing.

[17]  Bhiksha Raj,et al.  Scale independent raga identification using chromagram patterns and swara based features , 2013, 2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW).

[18]  Arvindh Krishnaswamy.  Melodic Atoms for Transcribing Carnatic Music , 2004, ISMIR.

[19]  Preeti Rao,et al.  A Survey of Raaga Recognition Techniques and Improvements to the State-of-the-Art , 2011 .

[20]  Hema A. Murthy,et al.  Raga Verification in Carnatic Music Using Longest Common Segment Set , 2015, ISMIR.