Abstract
Chroma conveying mainly a tonal content is considered as powerful representation that is widely used in musical information retrieval applications. In this paper, a new musical timbre description based only on the chromagram contours is investigated allowing the identification of both tonal content and particularly the instrument timbre (identity). After some steps of pre-processing and transformation, four methods are investigated as classifiers: support vector machine (SVM), neural network, invariant moments, and template matching based cross-correlation. All methods use only one pattern in training phase. Results are very promising and the graphical analysis demonstrates that contours are dependent on the music instrument. As first investigation, performance of about 70% is obtained with template matching and SVM classification techniques.
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Beauchamp, J.W.: Time-variant spectra of violin tones. Journal of the Acoustical Society of America 56(3), 995–1004 (1974)
Freedman, M.D.: Multidimensional perceptual scaling of musical timbres. Journal of the Acoustical Society of America 41(4A), 793–806 (1967)
Grey, J.M.: Multidimensional perceptual scaling of musical timbres. Journal of the Acoustical Society of America 61(5), 1270–1277 (1977)
Martin, K.D., Kim, Y.E.: Musical instrument identification: A pattern-recognition approach. Presented at the 136th Meeting of the Acoustical Society of America (1998)
Eronen, A.: Automatic Musical Instrument Recognition. Master’s thesis, Department of Information Technology, Tampere University of Technology, Tampere, Finland (2001)
Hall, G.-E., Ezzaidi, H., Bahoura, M.: Hierarchical parametrization and classification for instrument recognition. In: The 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA), Montreal, Canada, July 2-5, pp. 1066–1071 (2012)
Goto, M., Hashiguchi, H., Nishimura, T., Oka, R.: RWC Music Database: Music Genre Database and Musical Instrument Sound Database. In: The 4th International Conference on Music Information Retrieval (ISMIR 2003), Baltimore, Maryland, October 26-30, pp. 229–230 (2003)
Kitahara, T., Goto, M., Okuno, H.G.: Pitch-Dependent Identification of Musical Instrument Sounds. Applied Intelligence 23, 267–275 (2005)
Kitahara, T., Goto, M., Okuno, H.G.: Musical instrument identification based on F0-dependent multivariate normal distribution. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2003), April 6-10, vol. 5, pp. 421–424 (2003)
Ellis, D.: Classifying Music Audio with Timbral and Chroma Features. In: The 8th International Conference on Music Information Retrieval (ISMIR 2007), Vienna, Austria, September 23-30, pp. 339–340 (2007)
Hu, M.K.: Visual pattern recognition by moment invariants. IRE Transactions on Infomation Theory 8, 179–187 (1962)
Vapnik, V.N.: Statistical learning theory. John Wiley & Sons, Inc., New York (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ezzaidi, H., Bahoura, M., Hall, G.E. (2012). Towards a Characterization of Musical Timbre Based on Chroma Contours. In: Hassanien, A.E., Salem, AB.M., Ramadan, R., Kim, Th. (eds) Advanced Machine Learning Technologies and Applications. AMLTA 2012. Communications in Computer and Information Science, vol 322. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35326-0_17
Download citation
DOI: https://doi.org/10.1007/978-3-642-35326-0_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35325-3
Online ISBN: 978-3-642-35326-0
eBook Packages: Computer ScienceComputer Science (R0)