A Case Study About the Effort to Classify Music Intervals by Chroma and Spectrum Analysis

  • Verena Mattern
  • Igor Vatolkin
  • Günter Rudolph
Conference paper
Part of the Studies in Classification, Data Analysis, and Knowledge Organization book series (STUDIES CLASS)


Recognition of harmonic characteristics from polyphonic music, in particular intervals, can be very hard if the different instruments with their specific characteristics (overtones, formants, noisy components) are playing together at the same time. In our study we examined the impact of chroma features and spectrum on classification of single tone pitchs and music intervals played either by the same or different instruments. After the analysis of the audio recordings which produced the most errors we implemented two optimization approaches based on energy envelope and overtone distribution. The methods were compared during the experiment study. The results show that especially the integration of instrument-specific knowledge can significantly improve the overall performance.



We thank the Klaus Tschira Foundation for the financial support.


  1. Bartsch, M. A., & Wakefield, G. H. (2005). Audio thumbnailing of popular music using chroma-based representations. IEEE Transactions on Multimedia, 7(1), 96–104.CrossRefGoogle Scholar
  2. Eronen, A. (2009). Signal processing methods for audio classification and music content analysis. PhD thesis, Tampere University of Technology.Google Scholar
  3. Fujishima, T. (1999). Realtime chord recognition of musical sound: A system using common lisp music. In Proceedings of the international computer music conference (ICMC), Beijing (pp. 464–467).Google Scholar
  4. Gómez, E. (2006). Tonal description of music audio signals. PhD thesis, Universitat Pompeu Fabra, Department of Technology.Google Scholar
  5. Jourdain, R. (1998). Music, the brain and ecstasy: How music captures our imagination. New York: Harper Perennial.Google Scholar
  6. Lartillot, O., & Toiviainen, P. (2007). MIR in Matlab (II): A toolbox for musical feature extraction from audio. In Proceedings of the 8th international conference on music information retrieval (ISMIR) (pp. 127–130).Google Scholar
  7. Mauch, M. (2010). Automatic chord transcription from audio using computational models of musical context. PhD thesis, Queen Mary University of London.Google Scholar
  8. McGill University Master Samples.
  9. Müller, M., & Ewert, S. (2010). Towards timbre-invariant audio features for harmony-based music. IEEE Transactions on Audio, Speech, and Language Processing, 18(3), 649–662.CrossRefGoogle Scholar
  10. Park, T. H. (2010). Introduction to digital signal processing: Computer musically speaking (1st Ed.). Singapore/Hackensack: World Scientific Publishing Co. Pte. Ltd.Google Scholar
  11. Temperley, D. (2007). Music and probability. Cambridge, MA: MIT.MATHGoogle Scholar
  12. Theimer, W., Vatolkin, I., & Eronen, A. (2008). Definitions of audio features for music content description. Technical report TR08-2-001, University of Dortmund.Google Scholar
  13. Vatolkin, I., Theimer, W., & Botteck, M. (2010). Amuse (advanced mUSic explorer) – a multitool framework for music data analysis. In Proceedings of the 11th international society for music information retrieval conference (ISMIR), Utrecht (pp. 33–38).Google Scholar
  14. Witten, I. H., & Frank, E. (2005). Data mining: Practical machine learning tools and techniques. Amsterdam/Boston: Morgan Kaufmann.Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Verena Mattern
    • 1
  • Igor Vatolkin
    • 1
  • Günter Rudolph
    • 1
  1. 1.Algorithm EngineeringTU DortmundDortmundGermany

Personalised recommendations