Recognition of Voiceprint Using Deep Neural Network Combined with Support Vector Machine

  • Lv Han
  • Tianxing Li
  • Weijie Zheng
  • Tao Ma
  • Wenlian Ma
  • Sanzhi Shi
  • Xiaoning Jia
  • Linhua ZhouEmail author
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1084)


With the rapid development of artificial intelligence technology of deep learning method, it has been applied to many fields, especially to life science. In this paper, a novel approach for the task of voiceprint recognition was proposed. The combination of deep belief network (DBN) and support vector machine (SVM) was used to identify the voiceprint of 10 different individuals. Based on a 24-dimension Mel Frequency Cepstrum Coefficient (MFCC), the authors extracted 256-dimension deep voiceprint features via DBN model that is developed by stacking three layers of Restricted Boltzmann Machine (RBM), and conducted voiceprint recognition by approach of SVM. According to the recognition results, the new approach can significantly improve both of accuracy and efficiency when it was compared with traditional voiceprint features and recognition models. The low dimensional features of voiceprint was extracted into higher dimensions by DBN model, while SVM can avoid the elevation of computation complexity caused by the increases of feature dimension. The combined strengths have been fully expressed by the experimental results.


Voiceprint recognition Deep Neural Network Restricted Boltzmann Machine Support vector machine 



This work was partially supported by the National Natural Science Foundation of P. R. China (No. 11401092, 11426045), Scientific and Technological Planning Project of Ji Lin Province of P. R. China (No. 20180101229JC), Foundation of Ji Lin Educational Committee (No. JJKH20181100KJ).


  1. 1.
    Campbell, J.P.J.: Speaker recognition: a tutorial. Proc. IEEE 85(9), 1437–1462 (2008)CrossRefGoogle Scholar
  2. 2.
    Davis, S.B., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28(4), 357–366 (1980)CrossRefGoogle Scholar
  3. 3.
    Doddington, G.R.: Speaker recognition-identifying people by their voices. Proc. IEEE 73(11), 1651–1664 (1985)CrossRefGoogle Scholar
  4. 4.
    Shikano, K.: Text-independent speaker recognition experiments using codebooks in vector quantization. J. Acoust. Soc. Am. 77(S11), 57–68 (1985)Google Scholar
  5. 5.
    Waibel, A.: Modular Construction of Time-Delay Neural Networks for Speech Recognition. MIT Press, Cambridge (1989)CrossRefGoogle Scholar
  6. 6.
    Reynolds, D.A., Rose, R.C.: Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Trans. Speech Audio Process. 3(1), 72–83 (1995)CrossRefGoogle Scholar
  7. 7.
    Campbell, W.M., Sturim, D.E., Reynolds, D.A., et al.: SVM based speaker verification using a GMM super vector kernel and NAP variability compensation. In: IEEE International Conference on Acoustics, Speech and Signal Processing. ICASSP 2006 Proceedings, 2006:I-I. IEEE (2006)Google Scholar
  8. 8.
    Kenny, P., Boulianne, G., Ouelletm, P., Dumouchel, P.: Speaker and session variability in GMM-based speaker verification. IEEE Trans. Audio Speech Lang. Process. 15(4), 1448 (2007)CrossRefGoogle Scholar
  9. 9.
    Kenny, P., Boulianne, G., Ouellet, P., Dumouchel, P.: Speaker and session variability in GMM-based speaker verification. IEEE Trans. Audio Speech Lang. Process. 15(4), 1435–1447 (2007)CrossRefGoogle Scholar
  10. 10.
    Dehak, N., Kenny, P.J., Dehak, R., Dumouchel, P., Ouellet, P.: Front-end factor analysis for speaker verification. IEEE Trans. Audio Speech Lang. Process. 19(4), 788–798 (2011)CrossRefGoogle Scholar
  11. 11.
    Hinton, G.E., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Mohamed, A., Dahl, G., Hinton, G.: Deep belief networks for phone recognition. In: Nips Workshop on Deep Learning for Speech Recognition and Related Applications, vol. 1(9), pp. 39 (2009)Google Scholar
  13. 13.
    Hinton, G., Deng, L., Yu, D., et al.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 29(6), 82–97 (2012)CrossRefGoogle Scholar
  14. 14.
    Wu, M.: A Study of Text-Independent Speaker Recognition Based on Deep Learning. University of Science and Technology of China (2016)Google Scholar
  15. 15.
    Lv, L.: A Study of Voiceprint Recognition Methods based on Deep Learning. Southeast University (2016)Google Scholar
  16. 16.
    Zhijun, S., Lei, X., Yangming, X., et al.: The research overview of deep learning. Appl. Res. Comput. 29(8), 2806–2810 (2012)Google Scholar
  17. 17.
    Chunxia, Z., Nannan, J., Guanwei, W.: Restricted boltzmann machine. Chin. J. Eng. Math. 32(2), 161–175 (2015)MathSciNetzbMATHGoogle Scholar
  18. 18.
    Jinhui, L., Junan, Y., Yi, W.: New feature extraction method based on bottleneck deep belief networks and its application in language recognition. Comput. Sci. 41(3), 263–266 (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Lv Han
    • 1
  • Tianxing Li
    • 1
  • Weijie Zheng
    • 1
  • Tao Ma
    • 1
  • Wenlian Ma
    • 1
  • Sanzhi Shi
    • 1
  • Xiaoning Jia
    • 1
  • Linhua Zhou
    • 1
    Email author
  1. 1.School of Science, Department of Applied MathematicsChangchun University of Science and TechnologyChangchunChina

Personalised recommendations