Abstract
The research reported in this chapter is focused on automatic identification of musical instruments in polyphonic audio recordings. Random forests have been used as a classification tool, pre-trained as binary classifiers to indicate presence or absence of a target instrument. Feature set includes parameters describing frame-based properties of a sound. Moreover, in order to capture the patterns which emerge on the time scale, new temporal parameters are introduced to supply additional temporal information for the timbre recognition. In order to achieve higher estimation rate, we investigated a feature-driven hierarchical classification of musical instruments built using agglomerative clustering strategy. Experiments showed that the performance of classifiers based on this new classification of instruments schema is better than performance of the traditional flat classifiers, which directly estimate the instrument. Also, they outperform the classifiers based on the classical Hornbostel-Sachs schema.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
References
Breiman, L.: Random Forests. Machine Learning 45, 5–32 (2001)
Brown, J.C.: Computer identification of musical instruments using pattern recognition with cepstral coefficients as features. J. Acoust. Soc. Am. 105, 1933–1941 (1999)
Eggink, J., Brown, G.J.: Application of missing feature theory to the recognition of musical instruments in polyphonic audio. In: ISMIR 2003 (2003)
Foote, J.: An Overview of Audio Information Retrieval. Multimedia Systems 7, 2–11 (1999)
Goto, M., Hashiguchi, H., Nishimura, T., Oka, R.: RWC Music Database: Popular, Classical, and Jazz Music Databases. In: Proceedings of the 3rd International Conference on Music Information Retrieval, pp. 287–288 (2002)
Herrera-Boyer, P., Klapuri, A., Davy, M.: Automatic Classification of Pitched Musical Instrument Sounds. In: Klapuri, A., Davy, M. (eds.) Signal Processing Methods for Music Transcription. Springer Science & Business Media, LLC (2006)
Hornbostel, E.M., von Sachs, C.: Systematik der Musikinstrumente. Zeitschrift für Ethnologie 46, 553–590 (1914)
ISO MPEG-7 Overview, http://www.chiariglione.org/mpeg/
Klapuri, A., Davy, M. (eds.): Signal Processing Methods for Music Transcription. Springer, New York (2006)
Kostek, B.: Musical instrument classification and duet analysis employing music information retrieval techniques. Proc. IEEE 92(4), 712–729 (2004)
Kubera, E., Wieczorkowska, A., Raś, Z., Skrzypiec, M.: Recognition of Instrument Timbres in Real Polytimbral Audio Recordings. In: Balcázar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010. LNCS (LNAI), vol. 6322, pp. 97–110. Springer, Heidelberg (2010)
Kubera, E.: The role of temporal attributes in identifying instruments in polytimbral music recordings (in Polish). Ph.D. Dissertation, Polish-Japanese Institute of Information Technology (2010)
Liaw, A., Wiener, M.: Classification and regression by random Forest. R News 2(3), 18–22 (2002)
Livshin, A.A., Rodet, X.: Musical Instrument Identification in Continuous Recordings. In: Proc. of the 7th Int. Conference on Digital Audio Effects (DAFX 2004), Naples, Italy (2004)
MIDOMI, http://www.midomi.com/
Mierswa, I., Morik, K., Wurst, M.: Collaborative Use of Features in a Distributed System for the Organization of Music Collections. In: Shen, J., Shephard, J., Cui, B., Liu, L. (eds.) Intelligent Music Information Systems: Tools and Methodologies, pp. 147–176. IGI Global (2008)
Müller, M.: Information retrieval for music and motion. Springer, Heidelberg (2007)
Niewiadomy, D., Pelikant, A.: Implementation of MFCC vector generation in classification context. J. Applied Computer Science 16, 55–65 (2008)
Opolko, F., Wapnick, J.: MUMS – McGill University Master Samples. CD’s (1987)
R Development Core Team A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria, http://www.R-project.org
Raś, Z.W., Wieczorkowska, A.A. (eds.): Advances in Music Information Retrieval. SCI, vol. 274. Springer, Heidelberg (2010)
Shen, J., Shepherd, J., Cui, B., Liu, L. (eds.): Intelligent Music Information Systems: Tools and Methodologies. Information Science Reference, Hershey (2008)
Sony Ericsson TrackID, http://www.sonyericsson.com/trackid
The Pennsylvania State University Cluster Analysis - Ward’s Method, http://www.stat.psu.edu/online/courses/stat505/18_cluster/09_cluster_wards.html
The University of IOWA Electronic Music Studios Musical Instrument Samples, http://theremin.music.uiowa.edu/MIS.html
Zhang, X., Marasek, K., Raś, Z.W.: Maximum Likelihood Study for Sound Pattern Separation and Recognition. In: 2007 International Conference on Multimedia and Ubiquitous Engineering, MUE 2007, pp. 807–812. IEEE (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kubera, E., Wieczorkowska, A.A., Raś, Z.W. (2013). Time Variability-Based Hierarchic Recognition of Multiple Musical Instruments in Recordings. In: Skowron, A., Suraj, Z. (eds) Rough Sets and Intelligent Systems - Professor Zdzisław Pawlak in Memoriam. Intelligent Systems Reference Library, vol 43. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-30341-8_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-30341-8_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-30340-1
Online ISBN: 978-3-642-30341-8
eBook Packages: EngineeringEngineering (R0)