Skip to main content
SpringerLink
Log in

Cent Filter-Banks and its Relevance to Identifying the Main Song in Carnatic Music

  • Conference paper
  • First Online:
Sound, Music, and Motion (CMMR 2013)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 8905))

Included in the following conference series:

Abstract

Carnatic music is a classical music tradition from Southern India. It is primarily based on vocal music, where the lead performer is a singer. A typical Carnatic music concert is made up of several items. Each item can be made up of a number of segments, namely, monophonic vocal solo, monophonic violin solo, polyphonic (vocal and accompanying instruments) composition (or song) and monophonic percussion (thaniavarthanam). The composition (or song) segment is mandatory in every item. The identification of composition segments is necessary to determine the different items in a concert. Owing to the improvisation possibilities in a composition, the compositional segments can further consist of monophonic segments. The objective of this paper is to determine the location of song segments in a concert. The improvisational aspects of a concert lead to the number of applauses being much larger than the number of items. The concert is first segmented using the applauses. Next, inter-applause segments are classified as vocal solo, violin solo, composition and thaniavarthanam segments. Unlike Western music, the key used for different items in the concert is fixed by the performer. The key also referred to as tonic can vary from musician to musician and can also vary across concerts by the same musician. In order to classify different inter-applause segments across musicians, the features must be normalised with respect to the tonic. A new feature called Cent Filter-bank based Cepstral Coefficients (CFCC) that is tonic invariant is proposed. Song identification is performed on 50 live recordings of Carnatic music. The results are compared with that of the Mel Frequency Cepstral Coefficients (MFCC), and Chroma based Filter-bank Cepstral Coefficients (ChromaFCC). The song identification accuracy with MFCC is 80 %, with CFCC features is 95 % and with ChromaFCC features is 75 %. The results show that CFCC features give promising results for Carnatic music processing tasks.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    http://compmusic.upf.edu/.

  2. 2.

    http://www.sangeethapriya.org.

  3. 3.

    composition can also be referred as song (composition and song are interchangeably used in this paper).

  4. 4.

    www.ee.columbia.edu/~dpwe/resources/Matlab/chroma-ansyn.

  5. 5.

    Carnatic Music terms are explained in the Appendix.

  6. 6.

    Hereafter we refer to this as (main) song.

  7. 7.

    ALB-Alathur Brothers and Sanjay- Sanjay Subramanian.

  8. 8.

    DKP-DK Pattamal.

  9. 9.

    Labeling was done by the first author and verified by a professional musician.

  10. 10.

    These live recordings were obtained from a personal collection of audience, musicians. These were made available for research purposes only.

  11. 11.

    Labeling was done by the first author and verified by a professional musician.

References

  1. Ajmera, J., McCowan, I., Bourlard, H.: Speech/music segmentation using entropy and dynamism features in a HMM classification framework. Speech Commun. 40, 351–363 (2003)

    Article  Google Scholar 

  2. Alonso, M.A., Richard, G., David, B.: Tempo and beat estimation of musical signals. In: ISMIR (2004). http://dblp.uni-trier.de/db/conf/ismir/ismir2004.html#AlonsoRD04

  3. Anantapadmanabhan, A., Bello, J.P., Krishnan, R., Murthy, H.A.: Tonic-independent stroke transcription of the mridangam. In: AES 53rd International Conference on Semantic Audio. AES, London, 27 January 2014

    Google Scholar 

  4. Ananthapadmanabhan, A., Bellur, A., Murthy, H.A.: Modal analysis and transcription of strokes of the mridangam using non-negative matrix factorisation. In: Proceedings of IEEE Interntional Conference on Acoustics, Speech, and Signal Processing, Vancouver, Canada, May 2013

    Google Scholar 

  5. Bellur, A., Ishwar, V., Serra, X., Murthy, H.A.: A knowledge based signal processing approach to tonic identification in indian classical music. In: International CompMusic Wokshop, Instanbul, Turkey (2012)

    Google Scholar 

  6. Bellur, A., Murthy, H.A.: A cepstrum based approach for identifying tonic pitch in Indian classical music. In: National Conference on Communication, February 2013

    Google Scholar 

  7. Bellur, A., Murthy, H.A.: A novel application of group delay function for identifying tonic in Carnatic music. In: Proceedings of European Conference on Signal Processing, September 2013

    Google Scholar 

  8. Bozkurt, B.: Features for analysis of Makam music. In: Workshop on Computer Music, Instanbul, Turkey, July 2012

    Google Scholar 

  9. Brodsky, B.E., Darkhovsky, B.S.: Non-parametric Methods in Change-Point Problems. Kluwer Academic Publishers, New York (1993)

    Book  Google Scholar 

  10. Brown, J., Puckette, M.S.: An efficient algorithm for the calculation of a constant q transform. J. Acoust. Soc. Am. 92(5), 2698–2701 (1992)

    Article  Google Scholar 

  11. Cannam, C., Landone, C., Sandler, M., Bello, J.: The sonic visualiser: a visualisation platform for semantic descriptors from musical signals. In: 7th International Conference on Music Information Retrieval (ISMIR-06), Victoria, Canada (2006)

    Google Scholar 

  12. Chen, S., Gopalakrishnan, P.: Speaker, environment and channel change detection and clustering via the Bayesian Information Criterion. In: Proceedings of the DARPA Broadcast News Transcription and Understanding Workshop (1998). http://www.nist.gov/speech/publications/darpa98/pdf/bn20.pdf

  13. Cheveigne, A.D., Kawahara, H.: Yin, a fundamental frequency estimator for speech and music. J. Acoust. Soc. Am. 111(4), 1917–1930 (2002)

    Article  Google Scholar 

  14. Chordia, P.: Segmentation and recognition of tabla strokes. In: Proceedings of International Society for Music Information Retrieval (ISMIR) (2005)

    Google Scholar 

  15. Davis, S., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28, 357–366 (1980)

    Article  Google Scholar 

  16. Ellis, D.: Chroma feature analysis and synthesis (2007). http://www.ee.columbia.edu/~dpwe/resources/Matlab/chroma-ansyn

  17. Eronen, A., Klapuri, A.: Musical instrument recognition using cepstral coefficients and temporal features. In: Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, pp. II753-II756 (2000)

    Google Scholar 

  18. Gao, S., Maddage, N.C., Lee, C.H.: A hidden markov model based approach to music segmentation and identification. Technical report, International Conference on Information, Communications and Signal Processing (2003)

    Google Scholar 

  19. Gulati, S., Salamon, J., Serra, X.: A two-stage approach for tonic identification in indian art music. In: Workshop on Computer Music, Istanbul, Turkey, July 2012

    Google Scholar 

  20. Herrera, P., Peeters, G., Dubnov, S.: Automatic classification of musical instrument sounds. J. New Music Res. 32(1), 3–21 (2003)

    Article  Google Scholar 

  21. Ishwar, V., Bellur, A., Murthy, H.A.: Motivic analysis and its relevance to raga identification in carnatic music. In: Proceedings of the 2nd Computer Music Workshop, Istanbul, Turkey, July 2012

    Google Scholar 

  22. Ishwar, V., Dutta, S., Bellur, A., Murthy, H.A.: Motif spotting in an alapana in carnatic music. In: Proceedings of International Society for Music Information Retrieval (ISMIR), Curitiba, Brazil, November 2013

    Google Scholar 

  23. Koduri, G.K., Serra, J., Serra, X.: Characterization of Intonation in Karṇāṭaka Music by Parametrizing Context-based Svara Distributions. In: Workshop on Computer Music, Instanbul, Turkey, July 2012

    Google Scholar 

  24. Krishna, T.: A Southern Music: The Karnatik Story, 1st edn. HarperCollins Publishers in India, New Delhi (2013)

    Google Scholar 

  25. Krishnaswamy, A.: Inflexions and microtonality in south indian classical music. In: Frontiers of Research on Speech and Music (2004)

    Google Scholar 

  26. Krishnaswamy, A.: Multi-dimensional musical atoms in south-indian classical music. In: International Conference on Music Perception and Cognition (2004)

    Google Scholar 

  27. Logan, B.: Mel frequency cepstral coefficients for music modeling. In: International Symposium on Music Information Retrieval (2011)

    Google Scholar 

  28. Loughran, R., Walker, J., O’Neill, M., O’Farrell, M.: The use of mel-frequency cepstral coefficients in musical instrument identification. In: International Computer Music Conference, Ireland (2008)

    Google Scholar 

  29. Marolt, M.: Trancription of polyphonic piano music with neural networks. In: 10th Mediterranean Electrotechnical Conference, vol. 2, pp. 512–515 (2000).

    Google Scholar 

  30. Marques, J., Moreno, P.J.: A study of musical instrument classification using gaussian mixture models and support vector machines. Technical report, Compaq Corporation, Cambridge Research laboratory (1999)

    Google Scholar 

  31. Muller, M., Kurth, F., Clausen, M.: Audio matching via chroma-based statistical features. In: ISMIR (2005)

    Google Scholar 

  32. Murthy, M.V.N.: Applause and aesthetic experience (2012). http://compmusic.upf.edu/zh-hans/node/151

  33. Pesch, L.: The Oxford Illustrated Companion to South Indian Classical Music. Oxford University Press, Oxford (2009)

    Google Scholar 

  34. Ross, J.C., Rao, P.: Detection of Raga-characteristic phrases from Hindustani Classical Music Audio. In: Workshop on Computer Music, Instanbul, Turkey, July 2012

    Google Scholar 

  35. Ross, J.C., Vinutha, T., Rao, P.: Detecting melodic motifs from audio for hindustani classical music. In: Proceedings of International Society for Music Information Retrieval (ISMIR), Portugal, October 2012

    Google Scholar 

  36. Sarala, P., Ishwar, V., Bellur, A., Murthy, H.A.: Applause identification and its relevance to archival of carnatic music. In: Workshop on Computer Music, Instanbul, Turkey, July 2011

    Google Scholar 

  37. Sarala, P., Murthy, H.A.: Cent filter banks and its relevance to identifying the main song in carnatic music. In: Proceedings of Computer Music Multidsciplinary Research (CMMR), Marseille, France, October 2013

    Google Scholar 

  38. Sarala, P., Murthy, H.A.: Inter and intra item segmentation of continuous audio recordings of carnatic music for archival. In: Proceedings of International Society for Music Information Retrieval (ISMIR), Curitiba, Brazil, November 2013

    Google Scholar 

  39. Scheirer, E.D.: Tempo and beat analysis of acoustic musical signals. J. Acoust. Soc. Am. 103(1), 588–601 (1998). http://dx.doi.org/10.1121/1.421129

    Article  Google Scholar 

  40. Serra, J., Gomez, E., Herrera, P., Serra, X.: Chroma binary similarity and local alignment applied to cover song identification. IEEE Trans. Audio Speech Lang. Process. 16(6), 1138–1151 (2008)

    Article  Google Scholar 

  41. Serra, J., Koduri, G.K., Miron, M., Serra, X.: Tuning of sung indian classical music. In: Proceedings of ISMIR, pp. 157–162 (2011)

    Google Scholar 

  42. Serra, X.: Opportunities for a cultural specific approach in the computational description of music. In: Workshop on Computer Music, Istanbul, Turkey, July 2012

    Google Scholar 

  43. Srinivasamurthy, A., Subramanian, S., Tronel, G., Chordia, P.: A beat tracking approach to complete description of rhythm in indian classical music. In: Workshop on Computer Music, Instanbul, Turkey, July 2012

    Google Scholar 

  44. Srinivasasmurthy, A., Serra, X.: A supervised approach to hierarchical metrical cycle tracking from audio music recordings. In: Proceedings of IEEE International Conference Acoustics, Speech, and Signal Processing, May 2014

    Google Scholar 

  45. Tian, M., Srinivasasmurthy, A., Sandler, M., Serra, X.: A study of instrument-wise onset detection in beijing opera percussion ensembles. In: Proceedings of IEEE International Conference Acoustics, Speech, and Signal Processing, May 2014

    Google Scholar 

  46. Vidwans, A., Ganguli, K.K., Rao, P.: Classification of indian classical vocal styles from melodic contours. In: Workshop on Computer Music, Instanbul, Turkey, July 2012

    Google Scholar 

  47. Weng, C.W., Lin, C.Y., Jang, J.S.R.: Music instrument identification using mfcc: Erhu as an example. In: Proceedings of the 9th International Conference of the Asia Pacific Society for Ethnomusicology (Phnom Penh, Cambodia, 2004), Cambodia, pp. 42–43 (2004)

    Google Scholar 

Download references

Acknowledgments

This research was partly funded by the European Research Council under the European Unions Seventh Framework Program, as part of the CompMusic project (ERC grant agreement 267583).

Author information

Authors and Affiliations

  1. Indian Institute of Technology, Madras, 600036, India

    Padi Sarala & Hema A. Murthy

Authors
  1. Padi Sarala
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hema A. Murthy
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Padi Sarala .

Editor information

Editors and Affiliations

  1. CNRS - LMA, Marseille, France

    Mitsuko Aramaki

  2. Toulon-Var University and CNRS - LMA, Marseille, France

    Olivier Derrien

  3. CNRS - LMA, Marseille, France

    Richard Kronland-Martinet

  4. CNRS - LMA, Marseille, France

    Sølvi Ystad

Appendix: Carnatic Music Terms

Appendix: Carnatic Music Terms

  • Rāga alāpanā : Rāga alāpanā is an impromptu elaboration of the rāga at hand. There are no lyrics in an alāpanā.

  • Composition or Song: Song is a rendition of precomposed lyrics in a specific rāga and tala. It is set to predefined tune and elaborates the rāga.

  • Thanam: Thanam is another form of improvisation of the rāga using the syllables “Tha Nam”. Thanam has an intrinsic rhythm but does not follow any cyclic rhythmic structure.

  • Kalpana Svaram: In this kind of improvisation, the svaras/musical notes of that rāga are sung/played.

  • Niraval: A meaningful line from a composition is taken up for improvisation. The structure of the line is kept intact and the melody is improvised in the rāga in which the composition is set.

  • Thaniavarthanam: It is the term used for the mridangam solo performance in the concert.

  • Main Song: This terminology is used for the song which is chosen for extensive elaboration in the concert. It contains all the improvisational elements such as alāpanā, niraval, kalpana svaras. The main song always ends with the Thaniavarthanam.

  • Pallavi: A pallavi is a single line of music set to a thala. The pallavi has two parts, divided by an aridhi which is a pause between the two parts. The first part is called the purvanga and the second part after the aridhi is called the uttaranga. niraval is performed on the pallavi.

  • Ragam Thanam Pallavi: This piece is a combination of Rāga alāpanā, Thanam and the Pallavi. Hence the name, Ragam Thanam Pallavi(RTP).

  • Ragamalika: The performer, within a piece (for e.g.: RTP) performs many ragas at a stretch one after the other. This is known as a ragamalika. Literally it means, “A Chain of Ragas”.

  • Viruttham/slokha is an extempore free flow enunciation of a poem without rhythmic accompaniment. This poem if in the language sanskrit is called a slokha. The viruttham/slokha is rendered in a single rāga sometimes in multiple ragas.

  • Mangalam: Mangalam is the conclusive piece of every Carnatic music performance.

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer International Publishing Switzerland

About this paper

Cite this paper

Sarala, P., Murthy, H.A. (2014). Cent Filter-Banks and its Relevance to Identifying the Main Song in Carnatic Music. In: Aramaki, M., Derrien, O., Kronland-Martinet, R., Ystad, S. (eds) Sound, Music, and Motion. CMMR 2013. Lecture Notes in Computer Science(), vol 8905. Springer, Cham. https://doi.org/10.1007/978-3-319-12976-1_40

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-12976-1_40

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-12975-4

  • Online ISBN: 978-3-319-12976-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation