Abstract
The acoustic properties of wood for musical instruments have been often studied to manufacture good quality soundboards. The soundboard of a musical instrument plays an important role in producing good quality sound. Sape which is a Sarawak traditional musical instrument is a string instrument that is mostly made of a single bole of wood. Local woods such as Adau, Tapang, and Merbau were often used by the Sape makers to make the structure and soundboard of Sape. In this research, the objectives are to identify the feature of the selected wood type, classify the woods using machine learning, and propose the best wood to make the sape soundboard. Free-free beam forced vibration test is carried out to obtain the sound data from 9 wood samples. Acoustics, vibration, and timbre features are then ascertained. Support Vector Machine (SVM) algorithm is used to classify the wood type and wood grade using the 13 features selected. Wood is graded according to loudness and period. Adau wood which has a longer period and higher loudness tends to be the best wood type as the soundboard wood for making sape. The results show that the classification of the wood type and wood quality can be predicted using sound data collected from the flexural vibration of the Sape soundboard using MATLAB simulation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Fritz, C., Dubois, D.: Perceptual evaluation of musical instruments: state of the art and methodology. Acta Acust. Acust. 101(2), 369–381 (2015)
Yoshikawa, S.: Acoustical classification of woods for string instruments. J. Acoust. Soc. Am. 122(1), 568–573 (2007)
Fletcher, N.H., Rossing, T.D.: The physics of musical instruments. Springer (2012)
Wegst, U.G.: Wood for sound. Am. J. Bot. 93(10), 1439–1448 (2006)
Brémaud, I.: Acoustical properties of wood in string instruments soundboards and tuned idiophones: biological and cultural diversity. J. Acoust. Soc. Am. 131(1), 807–818 (2012)
Yang, Y., Liu, Y., Liu, Z., Shi, S.Q.: Prediction of Yueqin acoustic quality based on soundboard vibration performance using support vector machine. J. Wood Sci. 63(1), 37–44 (2016). https://doi.org/10.1007/s10086-016-1598-8
Norimoto, M.: Specific dynamic Young’s modulus and internal friction of wood in the longitudinal direction. Wood Res. Technol. Notes 22, 53–65 (1986)
Aramaki, M., et al.: Sound quality assessment of wood for xylophone bars. J. Acoust. Soc. Am. 121(4), 2407–2420 (2007)
Vapnik, V.: Statistical learning theory, vol. 1, p. 624. Wiley, New York (1998)
Nanda, M.A., et al.: A comparison study of kernel functions in the support vector machine and its application for termite detection. Information 9(1), 5 (2018)
Luo, W., Sun, L.: Wood defect detection and classification by fusion feature and support vector machine. J. Northeast Forestry Univ. 47(6), 70–73 (2019)
Redzuan, F.I.M., Yusoff, M.: Knots timber detection and classification with C-Support Vector Machine. Bull. Electr. Eng. Inform. 8(1), 246–252 (2019)
Lembaga Perindustrian Kayu, M.: 100 Malaysian timbers: 2010 edition. Kuala Lumpur [Malaysia]: Malaysian Timber Industry Board (2010)
Lee, Y.F.: Preferred Check-list of Sabah Trees. Natural History Pub. (Borneo) (2003)
Wegst, U.G.K.: Wood for sound. Am. J. Bot. 93, 1439–1448 (2006)
Brémaud, I., et al.: Characterisation and categorisation of the diversity in viscoelastic vibrational properties between 98 wood types. Ann. Forest Sci. 69 (2012)
Yoshikawa, S.: Acoustical classification of woods for string instruments. J. Acoust. Soc. Am. 122, 568–573 (2007)
Aramaki, M., et al.: Sound quality assessment of wood for xylophone bars. J. Acoust. Soc. Am. 121, 2407–2420 (2007)
Bishop, C.M., Nasrabadi, N.M.: Pattern Recognition and Machine Learning, vol. 4. Springer (2006)
Gu, I., Andersson, H., Vicen, R.: Wood defect classification based on image analysis and support vector machines. Wood Sci. Technol. 44, 693–704 (2009)
Acknowledgements
This work is financially supported by the University of Technology Sarawak through grant (4/2021/06), and partially funded by the TEPEN-ICF2021 grant (IF038–2022).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wong, T.H. et al. (2023). Classification of Sape Soundboard Wood Quality by Employing Machine Learning. In: Zhang, H., Ji, Y., Liu, T., Sun, X., Ball, A.D. (eds) Proceedings of TEPEN 2022. TEPEN 2022. Mechanisms and Machine Science, vol 129. Springer, Cham. https://doi.org/10.1007/978-3-031-26193-0_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-26193-0_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-26192-3
Online ISBN: 978-3-031-26193-0
eBook Packages: EngineeringEngineering (R0)