Music genre classification using spatan 6 FPGA and TMS320C6713 DSK

Music genre classification is one of the most important element of the music information retrieval (MIR) community. In this paper, we present a music genre classification system using field programmable gate arrays (FPGA) and dedicated DSP processors. The proposed system uses FPGA based acoustic feature extraction of mel frequency cepstral coefficients (MFCC) and dynamic time warping (DTW) based classifier using TMS320C6713 floating point processor. We successfully implemented MFCC extraction algorithm on Spartan 6 FPGA clocked at 150 MHz with support from TMS320C6713 floating point processor followed by DTW based matching engine. The paper attempts to implement music genre classification algorithm in hardware, yielding competitive performance in music information retrieval applications.

[1]  Shikha Tripathi,et al.  Real-time swara recognition system in Indian Music using TMS320C6713 , 2015, 2015 International Conference on Advances in Computing, Communications and Informatics (ICACCI).

[2]  A. N. Myna,et al.  Melody Information Retrieval System Using Dynamic Time Warping , 2009, CSIE.

[3]  Ali Shokoufandeh,et al.  Deep Neural Networks: A Case Study for Music Genre Classification , 2015, 2015 IEEE 14th International Conference on Machine Learning and Applications (ICMLA).

[4]  B. Venkataramani,et al.  Implementation of a Novel Phoneme Recognition System Using TMS320C6713 DSP , 2010, 2010 23rd International Conference on VLSI Design.

[5]  Abbes Amira,et al.  An efficient FPGA implementation of Gaussian mixture models based classifier: Application to face recognition , 2013, 2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA).

[6]  Olivier Romain,et al.  FPGA-based real-time MFCC extraction for automatic audio indexing on FM broadcast data , 2015, 2015 Conference on Design and Architectures for Signal and Image Processing (DASIP).

[7]  Yandre M. G. Costa,et al.  Music genre classification using visual features with feature selection , 2016, 2016 35th International Conference of the Chilean Computer Science Society (SCCC).

[8]  Mohammed Bahoura,et al.  Hardware implementation of MFCC feature extraction for respiratory sounds analysis , 2013, 2013 8th International Workshop on Systems, Signal Processing and their Applications (WoSSPA).

[9]  B. J. Sowmya,et al.  A comparative study of classifiers for music genre classification based on feature extractors , 2016, 2016 IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER).

[10]  A. S. Bhalerao,et al.  Implementation of automatic speaker recognition on TMS320C6713 using MFCC , 2013, 2013 International Conference on Computer Communication and Informatics.

[11]  F. Jawed,et al.  DSP Implementation of Voice Recognition Using Dynamic Time Warping Algorithm , 2005, 2005 Student Conference on Engineering Sciences and Technology.

[12]  Jinchang Ren,et al.  Embedded SVM on TMS320C6713 for signal prediction in classification and regression applications , 2012, 2012 5th European DSP Education and Research Conference (EDERC).

[13]  Bo Yu,et al.  A new hierarchical method for music genre classification , 2016, 2016 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).

[14]  Mohammed Bahoura,et al.  FPGA implementation of an automatic wheezes detector based on MFCC and SVM , 2016, 2016 2nd International Conference on Advanced Technologies for Signal and Image Processing (ATSIP).

[15]  Ettore Napoli,et al.  ASIC and FPGA Implementation of the Gaussian Mixture Model Algorithm for Real-Time Segmentation of High Definition Video , 2014, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[16]  Masahiko Yoshimoto,et al.  A low memory bandwidth Gaussian mixture model (GMM) processor for 20,000-word real-time speech recognition FPGA system , 2008, 2008 International Conference on Field-Programmable Technology.