Abstract
A head-related transfer function personalized algorithm based on Locally Linear Embedding is proposed for the precise localization of human beings with different physiological parameters. HRTF data was processed to reduce dimensionality by Locally Linear Embedding at first and linearly fitted in the low-dimensional space to extract the representative HRTF. Correlation analysis was used to select the physiological parameters which had a great influence on HRTF. The nonlinear mapping between physiological parameters and the representative HRTF was established by Artificial Neural Network, and then the individual HRTF can be calculated by a small number of body parameters. The experimental results show that the proposed algorithm can achieve personalized HRTF quickly and accurately, and solves the problem that personalized HRTF is difficult to measure.
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
Xie, B.: Head-Related Transfer Function database and its analysis. Sci. China Ser. G 50, 267 (2007). doi:10.1007/s11433-007-0018-x
Xu, S., Zeng, L., Li, Z., et al.: A pilot measurement of head-related transfer function blur in spatial localization. In: 2007 IEEE International Conference on Industrial Engineering and Engineering Management, Singapore, pp. 467–471 (2007)
Zotkin, D.N., Duraiswami, R., Davis, L.S., et al.: Virtual audio system customization using visual matching of ear parameters. In: 16th International Conference on Pattern Recognition (ICPR 2002), vol. 3, pp. 3–6 (2002)
Yin, T., Yu, G., He, Y., et al.: Simulation of individual head-related transfer functions using an improved head-neck-shoulder model. In: 21st International Congress on Sound and Vibration 2014: ICSV 21, vol. 3(6), pp. 1948–1953, Beijing, China, 13–17 July 2014
Ramos, O.A., Tommasini, F.C.: Magnitude modeling of HRTF using principal component analysis applied to complex value. Arch. Acoust. J. Pol. Acad. Sci. 39(4), 477–482 (2014)
Xiang, S., Nie, F., Pan, C., et al.: Regression reformulations of LLE and LTSA with locally linear transformation. IEEE Trans. Syst. Man Cybern. Part B Cyber. 41(5), 1250–1262 (2011). A publication of the IEEE Systems, Man, and Cybernetics Society
Zhang, T., Li, S., Wu, S., Tao, L.: Face recognition dimensionality reduction based on LLE and ISOMAP. In: Du, W. (ed.) Informatics and Management Science V, vol. 208, pp. 775–780. Springer, London (2013)
Jihua, Y., Shuxia, S., Yahui, C., et al.: A face recognition algorithm based on LLE-SIFT feature descriptors. In: 2015 10th International Conference on Computer Science Education (ICCSE 2015), pp. 729–734, Cambridge, UK, 22–24 July 2015
Algazi, V.R., Duda, R.O., Thompson, D.M., et al.: The CIPIC HRTF database. In: 2001 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics, pp. 99–102 (2001)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Ming, X., Binzhou, Y., Shuxia, G., Ying, G. (2018). Head-Related Transfer Function Individualization Based on Locally Linear Embedding. In: Qiao, F., Patnaik, S., Wang, J. (eds) Recent Developments in Mechatronics and Intelligent Robotics. ICMIR 2017. Advances in Intelligent Systems and Computing, vol 690. Springer, Cham. https://doi.org/10.1007/978-3-319-65978-7_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-65978-7_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-65977-0
Online ISBN: 978-3-319-65978-7
eBook Packages: EngineeringEngineering (R0)