Skip to main content
SpringerLink
Log in

Note Onset Detection with a Convolutional Neural Network in Recordings of Bowed String Instruments

  • Conference paper
  • First Online:
Multimedia Communications, Services and Security (MCSS 2017)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 785))

Abstract

In this article a convolutional neural network (CNN) is applied to the problem of note onset detection in music recordings. The work is focused on the analysis of pitched, non-percussive (PNP) onsets produced by bowed string instruments. Experimental evaluation is based on three datasets. The neural network has been trained on the largest one, which contains music excerpts of various kind. Two smaller datasets were used for testing. One of them is based on monophonic recordings of solo cello performances, while the other contains only polyphonic pieces for bowed string instruments (a violin duo and string ensembles).

The results obtained in experimental evaluation show that onset detection based on convolutional neural network trained with mixed audio material yields very good results in the case of solo cello recordings. For polyphonic bowed string instrument recordings, the overall detection efficacy is comparable to the general case, i.e. to the results obtained for mixed-genre, heterogeneous material. Detailed analysis shows that the method fails at detecting very “soft” note onsets present in some recordings.

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

References

  1. Bello, J., Daudet, L., Abdullah, S., Duxbury, C., Davies, M., Sandler, M.: A tutorial on onset detection in music signals. IEEE Trans. Speech Audio Process. 13(5), 1035–1047 (2005)

    Article  Google Scholar 

  2. Bello, P., Sandler, M.: Phase-based note onset detection for music signals. In: Proceedings of IEEE Conference on Acoustics, Speech, and Signal Processing ICASSP, vol. 5, pp. 441–444 (2003)

    Google Scholar 

  3. Böck, S., Arzt, A., Krebs, F., Schedl, M.: Online real-time onset detection with recurrent neural networks. In: Proceedings of the 15th International Conference on Digital Audio Effects (DAFx 2012) (2012)

    Google Scholar 

  4. Böck, S., Krebs, F., Widmer, G.: Joint beat and downbeat tracking with recurrent neural networks. In: Proceedings of the 17th International Society for Music Information Retrieval Conference, ISMIR 2016, New York City, United States, 7–11 August 2016, pp. 255–261 (2016)

    Google Scholar 

  5. Böck, S., Widmer, G.: Local group delay based vibrato and tremolo suppression for onset detection. In: Proceedings of the 13th International Society for Music Information Retrieval Conference (ISMIR 2013), Curitiba, Brazil, pp. 589–594, November 2013

    Google Scholar 

  6. Böck, S., Widmer, G.: Maximum filter vibrato suppression for onset detection. In: Proceedings of the 16th International Conference on Digital Audio Effects (DAFx 2013), Maynooth, Ireland, pp. 55–61 (2013)

    Google Scholar 

  7. Duxbury, C., Bello, J., Davies, M., Sandler, M.: Complex domain onset detection for musical signals. In: Proceedings of the 6th International Conference on Digital Audio Effects (DAFx 2003) (2003)

    Google Scholar 

  8. Eyben, F., Böck, S., Schuller, B., Graves, A.: Universal onset detection with bidirectional long short-term memory. In: Neural Networks, 11th International Society for Music Information Retrieval Conference (ISMIR 2010), pp. 589–594 (2010)

    Google Scholar 

  9. Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36, 193–202 (1980)

    Article  MATH  MathSciNet  Google Scholar 

  10. Holzapfel, A., Stylianou, Y., Gedik, A.C., Bozkurt, B.: Three dimensions of pitched instrument onset detection. IEEE Trans. Audio Speech Lang. Process. 18(6), 1517–1527 (2010)

    Article  Google Scholar 

  11. Hubel, D.H., Wiesel, T.N.: Receptive fields and functional architecture in two nonstriate visual areas (18 and 19) of the cat. J. Neurophysiol. 28, 229–289 (1965)

    Google Scholar 

  12. Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. arXiv preprint arXiv:1408.5093 (2014)

  13. Krebs, F., Böck, S., Dorfer, M., Widmer, G.: Downbeat tracking using beat synchronous features with recurrent neural networks. In: Proceedings of the 17th International Society for Music Information Retrieval Conference, ISMIR 2016, New York City, United States, 7–11 August 2016, pp. 129–135 (2016)

    Google Scholar 

  14. Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25, pp. 1097–1105. Curran Associates Inc., New York (2012)

    Google Scholar 

  15. Lacoste, A., Eck, D.: A supervised classification algorithm for note onset detection. EURASIP J. Adv. Sig. Process. 2007, 153 (2007)

    MATH  Google Scholar 

  16. LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)

    Article  Google Scholar 

  17. Lerch, A.: An Introduction to Audio Content Analysis: Applications in Signal Processing and Music Informatics. Wiley-IEEE Press, Hoboken (2012)

    Book  Google Scholar 

  18. Quintela, N.D., Giménez, A.P., Guijarro, S.T.: A comparison of score-level fusion rules for onset detection in music signals. In: Proceedings of 10th International Society for Music Information Retrieval Conference, ISMIR 2009, pp. 117–121, October 2009

    Google Scholar 

  19. Schlüter, J., Böck, S.: Musical onset detection with convolutional neural networks. In: 6th International Workshop on Machine Learning and Music (MML) (2013)

    Google Scholar 

  20. Schlüter, J., Bock, S.: Improved musical onset detection with convolutional neural networks. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2014), Florence, Italy (2014)

    Google Scholar 

  21. Soszyński, F., Wołowski, J., Stasiak, B.: Music games as a tool supporting music education. In: Proceedings of the Conference on Game Innovations, CGI 2016, pp. 116–132 (2016)

    Google Scholar 

  22. Stasiak, B., Mońko, J.: Analysis of onset detection with a maximum filter in recordings of bowed instruments. In: Proceedings of the 138th Audio Engineering Society Convention (2015)

    Google Scholar 

  23. Stasiak, B., Mońko, J., Niewiadomski, A.: Note onset detection in musical signals via neural-network-based multi-ODF fusion. Int. J. Appl. Math. Comput. Sci. 26(1), 203–213 (2016)

    Article  MathSciNet  Google Scholar 

  24. Stasiak, B., Monko, J.: Analysis of time-frequency representations for musical onset detection with convolutional neural network. In: Proceedings of the 2016 Federated Conference on Computer Science and Information Systems, FedCSIS 2016, pp. 147–152 (2016)

    Google Scholar 

  25. Thoshkahna, B., Ramakrishnan, K.R.: An onset detection algorithm for query by humming (QBH) applications using psychoacoustic knowledge. In: Proceedings of 17th European Signal Processing Conference, EUSIPCO 2009, pp. 939–942. IEEE (2009)

    Google Scholar 

  26. Tian, M., Fazekas, G., Black, D.A.A., Sandler, M.: Design and evaluation of onset detectors using different fusion policies. In: 15th International Society of Music Information Retrieval (ISMIR) Conference, pp. 631–636 (2014)

    Google Scholar 

  27. Wang, H., Wang, L.: Onset detection algorithm in voice activity detection for Mandarin. In: Proceedings of International Conference on Computer Science and Network Technology (ICCSNT), pp. 1148–1151 (2013)

    Google Scholar 

  28. Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. CoRR abs/1311.2901 (2013)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Institute of Information Technology, Łódź University of Technology, ul. Wólczańska 215, 93-005, Łódź, Poland

    Jędrzej Mońko & Bartłomiej Stasiak

Authors
  1. Jędrzej Mońko
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bartłomiej Stasiak
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bartłomiej Stasiak .

Editor information

Editors and Affiliations

  1. AGH University of Science and Technology, Krakow, Poland

    Andrzej Dziech

  2. Gdańsk University of Technology, Gdansk, Poland

    Andrzej Czyżewski

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Mońko, J., Stasiak, B. (2017). Note Onset Detection with a Convolutional Neural Network in Recordings of Bowed String Instruments. In: Dziech, A., Czyżewski, A. (eds) Multimedia Communications, Services and Security. MCSS 2017. Communications in Computer and Information Science, vol 785. Springer, Cham. https://doi.org/10.1007/978-3-319-69911-0_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-69911-0_14

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-69910-3

  • Online ISBN: 978-3-319-69911-0

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation