Biometric speech signal processing in a system with digital signal processor

Open access


This paper presents an analysis of issues related to the fixed-point implementation of a speech signal applied to biometric purposes. For preparing the system for automatic speaker identification and for experimental tests we have used the Matlab computing environment and the development software for Texas Instruments digital signal processors, namely the Code Composer Studio (CCS). The tested speech signals have been processed with the TMS320C5515 processor. The paper examines limitations associated with operation of the realized embedded system, demonstrates advantages and disadvantages of the technique of automatic software conversion from Matlab to the CCS and shows the impact of the fixed-point representation on the speech identification effectiveness.


  • [1] S. Furui, “50 years of progress in speech and speaker recognition”, ECTI Trans. on Computer and Information Technology 1 (2), 64-74 (2005).

  • [2] F. Bimbot, J. Bonastre, C. Fredouille, G. Gravier, I. Magrin- Chagnolleau, S. Meignier, T. Merlin, J. Ortega-Garcia, D. Petrovska-Delacretaz, and D. Reynolds, “A tutorial on textindependent speaker verification”, EURASIP J. on Applied Signal Processing 4, 430-451 (2004).

  • [3] S. Drgas and A. Dąbrowski, “Speaker recognition based on multilevel speech signal analysis on Polish corpus”, Multimedia Tools and Applications, Springer Verlang, DOI: 10.1007/s11042-013-1502-0 (2013).

  • [4] Y.S. Moon, C.C. Leung, and K.H. Pun, “Fixed-point GMMbased speaker verification over mobile embedded system”, Proc. 2003 ACM SIGMM Workshop on Biometrics Methods and Applications (WBMA’2003) 1, 53-57 (2003).

  • [5] P. Korohoda and A. Dąbrowski, “Generalized convolution as a tool for the multi-dimensional filtering tasks”, Multidimensional Systems and Signal Processing 19 (3-4), 361-377 (2008).

  • [6] Jhing-Fa Wang, Jr-Shiang Peng, Jia-Ching Wang, Po-Chuan Lin, and Ta-Wen Kuan, “Hardware/software co-design for fasttrainable speaker identification system based on SMO”, Proc. 2011 IEEE Int. Conf. on Systems, Man, and Cybernetics (SMC) 2, 1621-1625 (2011).

  • [7] Zhenling Zhang, Yangli Jia, and Guang Xie, “Design and implementation of speaker recognition system”, Proc. 2011 IEEE 2nd Int. Conf. on Software Engineering and Service Science (ICSESS) 1, 559-562 (2011).

  • [8] M. Lizondo, P.D. Ag¨uero, A.J. Uriz, J.C. Tulli, and E.L. Gonzalez, “Embedded speaker verification in low cost microcontroller”, Congreso Argentino de Sistemas Embebidos 1, 128-133 (2012).

  • [9] TMS320C5515 Fixed-Point Digital Signal Processor, SPRS645E VIII 2010, REV I, Texas Instruments (2012).

  • [10] FFT Implementation on the TMS320VC5505, TMS320C5505, and TMS320C5515 DSPs (Rev. B), Texas Instruments (2013).

  • [11] M. Siwczyński, A. Drwal, and S. Żaba, “The digital function filters - algorithms and applications”, Bull. Pol. Ac. Tech. 61 (2), 371-377 (2013).

  • [12] T. Marciniak, R. Weychan, S. Drgas, A. Dąbrowski, and A. Krzykowska, “Speaker recognition based on short Polish sequences”, Proc. IEEE Signal Processing Conf. (SPA’2010) 1, 95-98 (2010).

  • [13] A. Dąbrowski, S. Drgas, and T. Marciniak, “Detection of GSM speech coding for telephone call classification and automatic speaker recognition”, Proc. Int. Conf. on Signals and Electronic Systems (ICSES’2008) 1, 415-418 (2008).

  • [14] R. Weychan and T. Marciniak, “Analysis of differences between MFCC after multiple GSM transcodings”, Przeglad Elektrotechniczny 88 (6), 24-29 (2012).

  • [15] A. Krzykowska, T. Marciniak, R. Weychan, and A. Dąbrowski, “Influence of GSM coding on speaker recognition using Polish short sequences”, Proc. Joint Conf. New Trends in Audio and Video and IEEE Signal Processing Conf. (NTAV/SPA’2012) 1, 197-202 (2012).

  • [16] TMS320C5515 eZDSP USB Stick Technical Reference, 512845-0001 Rev A II, Spectrum Digital (2010).

  • [17] Matlab Coder Generate C and C++ Code from MATLAB Code, MathWorks, Inc. (2012).

  • [18] T. Marciniak, A. Krzykowska, and R. Weychan, “Speaker recognition based on telephone quality short Polish sequences with removed silence”, Przegląd Elektrotechniczny 88 (6), 42-46 (2012).

  • [19] R. Weychan, A. Stankiewicz, T. Marciniak, and A. Dąbrowski, “Analysis of the impact of data resolution on the speaker recognition effectiveness in embedded fixed-point systems”, Proc. IEEE Signal Processing Conference (SPA’2013) 1, 327-331 (2013).

  • [20] R. Suszyński and K. Wawryn, “Rapid prototyping of algorithmic A/D convertets based on FPAA devices”, Bull. Pol. Ac. Tech. 61 (3), 691-696 (2013).

Bulletin of the Polish Academy of Sciences Technical Sciences

The Journal of Polish Academy of Sciences

Journal Information

IMPACT FACTOR 2016: 1.156
5-year IMPACT FACTOR: 1.238

CiteScore 2016: 1.50

SCImago Journal Rank (SJR) 2016: 0.457
Source Normalized Impact per Paper (SNIP) 2016: 1.239


All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 10 10 10
PDF Downloads 2 2 2