Abstract
Today, stationary systems like personal computers and even portable music playback devices provide storage capacities for huge music collections of several thousand files. Therefore, the automated music classification is a very attractive feature for managing such multimedia databases. This type of application enhances the user comfort by classifying songs into predefined categories like music genres or user-defined categories. However, the automated music classification, based on audio feature extraction, is, firstly, extremely computation intensive, and secondly, has to be applied to enormous amounts of data. This is the reason why energy-efficient high-performance implementations for feature extraction are required. This contribution presents a dedicated hardware architecture for music classification applying typical audio features for discrimination (e.g., spectral centroid, zero crossing rate). For evaluation purposes, the architecture is mapped on an Field Programmable Gate Array (FPGA). In addition, the same application is also implemented on a commercial Graphics Processing Unit (GPU). Both implementations are evaluated in terms of processing time and energy efficiency.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Rodellar-Biarge, V., Gonzalez-Concejero, C., Martinez De Icaya, E., Alvarez-Marquina, A., & Gómez-Vilda, P. (2007). Hardware reusable design of feature extraction for distributed speech recognition, proceedings of the 6th WSEAS international conference on applications of electrical engineering, Istanbul, Turkey (pp. 47–52).
Blume, H., Haller, M., Botteck, M., & Theimer, W. (2008). Perceptual feature based music classification a DSP perspective for a new type of application, proceedings of the SAMOS VIII conference (IC-SAMOS), (pp. 92–99).
Blume, H., Bischl, B., Botteck, M., Igel, C., Martin, R., Roetter, G., Rudolph, G., Theimer, W., Vatolkin, I., & Weihs, C. (2011). Huge music archives on mobile devices – Toward an automated dynamic organization. IEEE Signal Processing Magazine, Special Issue on Mobile Media Search, 28(4), 24–39.
Friedrich, T., Gruhne, M., & Schuller, G. (2008). A fast feature extraction system on compressed audio data, audio engineering society, 124th convention, Netherlands.
Fu, Z., Lu, G., Ting, K. M., & Zhang, D. (2011). A survey of audio-based music classification and annotation. IEEE Transactions on Multimedia, 13, 303–319.
Kuon, I., & Rose, J. (2007). Measuring the gap between FPGAs and ASICs, IEEE transactions on computer-aided design of integrated circuits and systems, Dortmund, Germany, Vol. 26 (pp. 203–215).
Schmaedecke, I., Moerschbach, & J., Blume, H. (2011). GPU-based acoustic feature extraction for electronic media processing, proceedings of the 14th ITG conference, Dortmund, Germany.
Schmidt, E., West, K., & Kim, Y. (2009). Efficient acoustic feature extraction for music information retrieval using programmable gate arrays, Kobe, Japan, ISMIR 2009.
Tzanetakis, G., & Cook, P. (2002). Musical genre classification of audio signals. IEEE Transaction on Speech and Audio Processing, 10(5), 293–302.
Underwood, K. D., & Hemmert, K. S. (2008). The implications of floating point for FPGAs. In S. Hauck and A. Dehon, (Eds.), Reconfigurable computing (pp. 671–695). Boston: Elsevier.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer International Publishing Switzerland
About this paper
Cite this paper
Schmädecke, I., Blume, H. (2013). High Performance Hardware Architectures for Automated Music Classification. In: Lausen, B., Van den Poel, D., Ultsch, A. (eds) Algorithms from and for Nature and Life. Studies in Classification, Data Analysis, and Knowledge Organization. Springer, Cham. https://doi.org/10.1007/978-3-319-00035-0_55
Download citation
DOI: https://doi.org/10.1007/978-3-319-00035-0_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-00034-3
Online ISBN: 978-3-319-00035-0
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)