Abstract
Instrument recognition is an important task in music information retrieval (MIR). Whereas the recognition of musical instruments in monophonic recordings has been studied widely, the polyphonic case still is far from being solved. A new approach towards feature-based instrument recognition is presented that makes use of redundancies in the harmonic structure and temporal development of a note. The structure of the proposed method is targeted at transferability towards use on polyphonic material. Multiple feature categories are extracted and classified separately with SVM models. In a further step, class probabilities are aggregated in a two-step combination scheme. The presented system was evaluated on a dataset of 3300 isolated single notes. Different aggregation methods are compared. As the results of the joined classification outperform individual categories, further development of the presented technique is motivated.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
The so-called string beating occurs with string instruments (e.g., guitar or piano) and is caused through superimpositions of closely pitched oscillation modes.
- 2.
Subharmonics can for instance be observed in flageolet tones from string instruments as well as in brass instrument notes.
- 3.
The LIBSVM implementation, as described in [4] was used.
- 4.
note\(|\)partials\(|\)frames spectral\(|\)frames harmonic.
- 5.
References
Barbedo, J.G.A., Tzanetakis, G.: Instrument identification in polyphonic music signals based on individual partials. In: Proceedings of the 2010 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Dallas, Texas, USA, pp. 401–404 (2010). http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5495794, http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5495794
Bosch, J.J., Janer, J., Fuhrmann, F., Herrera, P.: A comparison of sound segregation techniques for predominant instrument recognition in musical audio signals. In: Proceedings of the 13th International Society for Music Information Retrieval Conference (ISMIR), Porto, Portugal, pp. 559–564 (2012). http://ismir2012.ismir.net/event/papers/559-ismir-2012.pdf
Brown, J.C., Houix, O., McAdams, S.: Feature dependence in the automatic identification of musical woodwind instruments. J. Acoust. Soc. Am. 109(3), 1064–1071 (2001). http://link.aip.org/link/JASMAN/v109/i3/p1064/s1&Agg=doi
Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. Technical report, Department of Computer Science, National Taiwan University, Taipei, Taiwan (2013)
Eronen, A.: Comparison of features for musical instrument recognition. In: Proceedings of the 2001 IEEE Workshop on the Applications of Signal Processing to Audio and Acoustics (WASPAA), Mohonk, New York, USA, pp. 19–22 (2001). http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=969532, http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=969532
Fritts, L.: University of Iowa musical instrument sample database (1997). http://theremin.music.uiowa.edu/MIS.html
Fuhrmann, F., Haro, M., Herrera, P.: Scalability, generality and temporal aspects in automatic recognition of predominant musical instruments in polyphonic music. In: Proceedings of the 10th International Society for Music Information Retrieval Conference (ISMIR), Kobe, Japan, pp. 321–326 (2009). http://ismir2009.ismir.net/proceedings/OS3-1.pdf
Fuhrmann, F., Herrera, P.: Polyphonic instrument recognition for exploring semantic similarities in music. In: Proceedings of the 13th International Conference on Digital Audio Effects (DAFx), Graz, Austria (2010). http://mtg.upf.es/system/files/publications/ffuhrmann_dafx10_final.pdf
Goto, M., Hashiguchi, H., Nishimura, T., Oka, R.: RWC music database. In: Proceedings of the 4th International Society for Music Information Retrieval Conference (ISMIR), Baltimore, Maryland, USA, pp. 229–230 (2003). http://ukpmc.ac.uk/abstract/CIT/688685
Itoyama, K., Goto, M., Komatani, K., Ogata, T., Okuno, H.G.: Simultaneous processing of sound source separation and musical instrument identification using Bayesian spectral modeling. In: Proceedings of the 2011 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), No. 3, Prague, Czech Republic, pp. 3816–3819 (2011). http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=5947183, http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=5947183
Joder, C., Essid, S., Richard, G.: Temporal integration for audio classification with application to musical instrument classification. IEEE Trans. Audio Speech Lang. Process. 17(1), 174–186 (2009). http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4740151, http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=4740151
Kinoshita, T., Sakai, S., Tanaka, H.: Musical sound source identification based on frequency component adaptation. In: Proceedings of the Workshop on Computational Auditory Scene Analysis (IJCAI-CASA), Stockholm, Sweden, pp. 18–24 (1999). http://lab.iisec.ac.jp/~tanaka_lab/publications/pdf/conference/conference-99-04.pdf
Kitahara, T., Goto, M., Okuno, H.G.: Musical instrument identification based on F0-dependent multivariate normal distribution. In: Proceedings of the 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Hong Kong, China, vol. 5, pp. 421–424 (2003). http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1199996, http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=1199996
Opolko, F., Wapnick, J.: The McGill University Master Samples Collection on DVD (3 DVDs) (2006)
Peeters, G.: A large set of audio features for sound description (similarity and classification) in the CUIDADO project. Technical report, IRCAM, Paris, France (2004). http://www.citeulike.org/group/1854/article/1562527
Tjoa, S., Liu, K.J.R.: Musical instrument recognition using biologically inspired filtering of temporal dictionary atoms. In: Proceedings of the 11th International Society for Music Information Retrieval Conference (ISMIR), Utrecht, The Netherlands, pp. 435–440 (2010). http://www.mirlab.org/conference_papers/International_Conference/ISMIR2010/ISMIR_2010_papers/ismir2010-74.pdf
Acknowledgments
This research work is a part of the SyncGlobal project. It is a 2-year collaborative research project between piranha womex AG from Berlin and Bach Technology GmbH, 4FriendsOnly AG, and Fraunhofer IDMT in Ilmenau, Germany. The project is co-financed by the German Ministry of Education and Research within the framework of an SME innovation program (FKZ 01/S11007).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Grasis, M., Abeßer, J., Dittmar, C., Lukashevich, H. (2014). A Multiple-Expert Framework for Instrument Recognition. 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_38
Download citation
DOI: https://doi.org/10.1007/978-3-319-12976-1_38
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)