Abstract
Using audio fingerprint for representing the audio content is a simple way for detecting similar songs with increasing the accuracy. This becomes more important problem when we need to handle ten million songs in the Internet. Not only the goodness of audio fingerprint extraction algorithm, but also the searching algorithm can affect much the effectiveness of searching system. In previous work, we proposed a new massively parallel system that can handle the audio fingerprint searching problem for thousands of queries at the same time based on HiFP2.0 audio fingerprint extraction algorithm. Our system uses LSH and K-modes for combining the data-flow from CPU to GPGPUs. In this paper, we continue proposing methods for increasing the accuracy of our system and increasing efficiency of massively parallel. We also propose new cluster algorithm extended from K-modes that can meet the requirements for GPGPU system with different size devices.
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
Yang, F., Sato, Y., Tan , Y., Inoguchi, Y.: Searching acceleration for audio fingerprinting system. In: Joint Conference of Hokuriku Chapters of Electrical Societies (2012)
Cano, P., Batlle, E.: A Review of Algorithms for Audio Fingerprinting, 9–11 December 2002. - 0–7803-7713-3
Haitsma, J., Kalker, T.: A highly robust audio fingerprinting system. J. New Music Res. 32(2), 211–222 (2003)
Huang, Z.: Extensions to the K-Means algorithm for clustering large data sets with categorical values. Data Min. Knowl. Discov. 2(3), 283–304 (1998)
Jgou, H., Amsaleg, L., Schmid, C., Gros, P.: Query-adaptive locality sensitive hashing, 31 March 2008–4 April 2008. 978-1-4244-1483-3
Andoni, A., Indyk, P.: Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions, October 2006. 0–7695-2720-5
Indyk, P., Motwani, R.: Approximate nearest neighbors: towards removing the curse of dimensionality. In: Proceedings of the Thirtieth Annual ACM Symposium on Theory of Computing, STOC 1998, pp. 604–613. ISBN: 0-89791-962-9 (1998)
Huang, J.Z.: Clustering Categorical Data with k-Modes. Encyclopedia of Data Warehousing and Mining, 2nd edn. IGI Publishing, Hershey (2009)
Huang, Z., Ng, M.K.: A fuzzy \(k\)-Modes algorithm for clustering categorical data. IEEE Trans. Fuzzy Syst. 7(4), 446–452 (1999)
Garcia, V., Debreuve, E., Barlaud, M.: Fast k nearest neighbor search using GPU. In: IEEE Computer Society Conference on Proceeding Computer Vision and Pattern Recognition Workshops, CVPRW 2008. IEEE (2008)
Nguyen, M.T., Inoguchi, Y.: Audio fingerprint hierarchy searching on massively parallel with multi-GPGPUs using K-modes and LSH. In: The Eighth International Conference on Knowledge and Systems Engineering (KSE 2016) (2016)
Fang, J., Varbanescu, A.L., Sips, H.: A comprehensive performance comparison of CUDA and OpenCL, 13–16 September 2011. 978-1-4577-1336-1
Inam, R.: An Introduction to GPGPU Programming- CUDA Architecture
Acknowledgment
The authors would like to thank JAIST-scholarship for assistance with expenses for maintaining the studies and laboratories.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Mau, T.N., Inoguchi, Y. (2017). Robust Optimization for Audio FingerPrint Hierarchy Searching on Massively Parallel with Multi-GPGPUs Using K-modes and LSH. In: Duy, V., Dao, T., Kim, S., Tien, N., Zelinka, I. (eds) AETA 2016: Recent Advances in Electrical Engineering and Related Sciences. AETA 2016. Lecture Notes in Electrical Engineering, vol 415. Springer, Cham. https://doi.org/10.1007/978-3-319-50904-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-50904-4_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-50903-7
Online ISBN: 978-3-319-50904-4
eBook Packages: EngineeringEngineering (R0)