Text–Independent Speaker Recognition Using Two–Dimensional Information Entropy

Božilović, Boško; Todorović, Branislav M.; Obradović, Miroslav

doi:10.2478/jee-2015-0027

Abstract

Speaker recognition is the process of automatically recognizing who is speaking on the basis of speaker specific characteristics included in the speech signal. These speaker specific characteristics are called features. Over the past decades, extensive research has been carried out on various possible speech signal features obtained from signal in time or frequency domain. The objective of this paper is to introduce two-dimensional information entropy as a new text-independent speaker recognition feature. Computations are performed in time domain with real numbers exclusively. Experimental results show that the two-dimensional information entropy is a speaker specific characteristic, useful for speaker recognition.

References

[1] Biometric Recognition: Challenges and Opportunities (Pato, J. , Millett, L. I., eds.), National Academies Press, Washington, 2010.
Search in Google Scholar
[2] TOGNERI, R.-PULLELLA, D. : An Overview of Speaker Identification: Accuracy and Robustness Issues, IEEE Circuits and Systems Magazine, Second quarter (2011), 23-61.10.1109/MCAS.2011.941079
Search in Google Scholar
[3] CAMPBELL, J. P. : Speaker Recognition: A Tutorial, Proc. of the IEEE 85 No. 9 (1997), 1437-1462.10.1109/5.628714
Search in Google Scholar
[4] ROSE, P. : Forensic Speaker Identification, Taylor & Francis, London, 2002.10.1201/9780203166369
Search in Google Scholar
[5] KINNUNEN, T. : Spectral Features for Automatic Text-Inde- pendent Speaker Recognition, Licentiate’s thesis, University of Joensuu, Joensuu, Finland, 2003.
Search in Google Scholar
[6] KINNUNEN, T. : Optimizing Spectral Feature Based Text-In- dependent Speaker Recognition, PhD thesis, University of Joensuu, Joensuu, Finland, 2005.
Search in Google Scholar
[7] JIN, Q.-SCHULTZ, T.-WAIBEL, A. : Phonetic Speaker Identification, Proc. of the Int. Conference of Spoken Language Processing (ICSLP 2002), Denver, CO, Sep 2002, pp. 1345-1348.10.21437/ICSLP.2002-409
Search in Google Scholar
[8] BACHOROWSKI, J. A.-OWREN, M. J. : Acoustic Correlates of Talker Sex and Individual Talker Identity are Present in a Short Vowel Segment Produced in Running Speech, Journal of Acoust. Soc. America. 106 No. 2 (1999), 1054-1063.10.1121/1.427115
Search in Google Scholar
[9] ADAMI, A. G. : Modeling Prosodic Differences for Speaker Recognition, Speech Communication 49 No. 4 (2007), 277-291.10.1016/j.specom.2007.02.005
Search in Google Scholar
[10] FURUI, S. : Digital Speech Processing, Synthesis, and Recognition, 2nd ed., Marcel Dekker, New York, 2001.
Search in Google Scholar
[11] SIVAKUMARAN, P.-ARIYAEEINIA, A.-LOOMES, M. : Sub-Band Based Text-Dependent Speaker Verification, Speech Communication 41 No. 2-3 (2003), 485-509.10.1016/S0167-6393(03)00017-7
Search in Google Scholar
[12] DAVIS, S.-MERMELSTEIN, P. : Comparison of Parametric Representations for Monosyllabic Word Recognition in Continuously Spoken Sentences, IEEE Trans. Acoustics, Speech, Signal Processing 28 No. 4 (1980), 357-366.
Search in Google Scholar
[13] HERMANSKY, H. : Perceptual Linear Predictive (PLP) Analysis of Speech, Journal Acoust. Soc. America, 87 No. 4 (1990), 1738-1752.
Search in Google Scholar
[14] MAMMONE, R.-ZHANG, X.-RAMACHANDRAN, R. : Ro- bust Speaker Recognition: a Feature Based Approach, IEEE Signal Processing Magazine 13 No. 5 (1996), 58-71.10.1109/79.536825
Search in Google Scholar
[15] NOLAN, F. : The Phonetic Bases of Speaker Recognition, Cam- bridge, 1983.
Search in Google Scholar
[16] ANTAL, M. : Phonetic Speaker Recognition, Proc. of 7th Int. Conference Communications, Bucharest, Romania, June 2008, pp. 67-72.
Search in Google Scholar
[17] DEHAK, N.-KENNY, P.-DUMOUCHEL, P. : Modeling Prosodic Features with Joint Factor Analysis for Speaker Verification, IEEE Trans. Audio, Speech and Language Processing 15 No. 7 (2007), 2095-2103.10.1109/TASL.2007.902758
Search in Google Scholar
[18] MILIVOJEVI´C, Z. N.-BRODI´C, D. : Estimation of the Funda- mental Frequency of the Speech Signal Compressed by G.723.1 Algorithm Applying PCC Interpolation, Journal of Electrical Engineering, 62 No. 4 (2011), 181-189.
Search in Google Scholar
[19] KINNUNEN, T.-LI, H. : An Overview of Text-Independent Speaker Recognition: From features to Supervectors, Speech Communication 52 No. 1 (2010), 12-40.10.1016/j.specom.2009.08.009
Search in Google Scholar
[20] SEDLAK, V.-DURACKOVA, D.-ZALUSKY.-KOVA- CIK, T. : Intelligibility Assessment of Ideal Binary-Masked Noisy Speech with Acceptance of Room Acoustic, Journal of Electrical Engineering 65 No. 6 (2014), 325-332.
Search in Google Scholar
[21] PRIBIL, J.-PRIBILOVA, A.-DURACKOVA, D. : An Experiment with Spectral Analysis of Emotional Speech Affected by Orthodontic Appliances, Journal of Electrical Engineering 63 No. 5 (2012), 296-302.10.2478/v10187-012-0043-5
Search in Google Scholar
[22] O’SHAUGHNESSY, D. Automatic Speech Recognition: History, Methods and Challenges : Pattern Recognition 41 (2008), 2965-2979.
Search in Google Scholar
[23] VASEGHI, S. V. : Multimedia Signal Processing: Theory and Applications in Speech, Music and Communications, JohnWiley & Sons, 2007.10.1002/9780470066508
Search in Google Scholar
[24] BRUMMER, N.-du PREEZ, J. : Application Independent Evaluation of Speaker Detection, Computer Speech and Language 20 No. 2-3 (2006), 230-275.10.1016/j.csl.2005.08.001
Search in Google Scholar
[25] ARONOWITZ, H.-BURSHTEIN, D. :Efficient Speaker Recognition using Approximated Cross Entropy (ACE), IEEE Trans- actions on Audio, Speech and Language Processing 15 No. 7 (Sep 2007), 2033-2043.10.1109/TASL.2007.902059
Search in Google Scholar
[26] GIANNAKOPOULOS, T. : Silence Removal in Speech Signals, MATLAB Central, March 2014, available from: http://www.mathworks.com/matlabcentral/fileexchange/28826-silence-removal-in-speech-signals, accessed on December 14, 2014.
Search in Google Scholar
[27] SOONG, F. K.-ROSENBERG, A. E.-JUANG, B. H.-RABINER, L. R. : A Vector Quantization Approach to Speaker Recognition, AT&T Technical Journal 66 No. 2 (Mar-Apr 1987), 14-26.10.1002/j.1538-7305.1987.tb00198.x
Search in Google Scholar
[28] LINDE, Y.-BUZO, A.-GRAY, R. : An Algorithm for Vector Quantizer Design, IEEE Trans. on Communications 28 No. 1 (1980), 84-95.10.1109/TCOM.1980.1094577
Search in Google Scholar
[29] REYNOLDS, D. A.-ROSE, R. C. : Robust Text Independent Speaker Identification using Gaussian Mixture Speaker Models, IEEE Trans. on Speech and Audio Processing 3 No. 1 (1995), 72-83.10.1109/89.365379
Search in Google Scholar
[30] Barclays International Banking, available from: https://wealth.barclays.com/en_gb/internationalwealth/manage-your-money/banking-on-the-power-of-speech.html, accessed on December 14, 2014.
Search in Google Scholar

Text–Independent Speaker Recognition Using Two–Dimensional Information Entropy

Abstract

Paradigm

My account