Spin-Image Descriptors for Text-Independent Speaker Recognition

  • Suhaila N. MohammedEmail author
  • Adnan J. Jabir
  • Zaid Ali Abbas
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1073)


Building a system to identify individuals through their speech recording can find its application in diverse areas, such as telephone shopping, voice mail and security control. However, building such systems is a tricky task because of the vast range of differences in the human voice. Thus, selecting strong features becomes very crucial for the recognition system. Therefore, a speaker recognition system based on new spin-image descriptors (SISR) is proposed in this paper. In the proposed system, circular windows (spins) are extracted from the frequency domain of the spectrogram image of the sound, and then a run length matrix is built for each spin, to work as a base for feature extraction tasks. Five different descriptors are generated from the run length matrix within each spin and the final feature vector is then used to populate a deep belief network for classification purpose. The proposed SISR system is evaluated using the English language Speech Database for Speaker Recognition (ELSDSR) database. The experimental results were achieved with 96.46 accuracy; showing that the proposed SISR system outperforms those reported in the related current research work in terms of recognition accuracy.


Deep belief network Run length matrix Speaker recognition Speech spectrogram image Spin-based descriptors 


  1. 1.
    Kekre, H.B., Kulkarni, V., Gaikar, P., Gupta, N.: Speaker identification using spectrograms of varying frame sizes. Int. J. Comput. Appl. 50(20), 27–33 (2012)Google Scholar
  2. 2.
    Dhakal, P., Damacharla, P., Javaid, A.Y.: A near real-time automatic speaker recognition architecture for voice-based user interface. Mach. Learn. Knowl. Extr. 1, 504–520 (2019)CrossRefGoogle Scholar
  3. 3.
    Chauhan, T., Soni, H., Zafar, S.: A review of automatic speaker recognition system. Int. J. Soft Comput. Eng. (IJSCE) 3(4), 132–135 (2013)Google Scholar
  4. 4.
    Fandrianto, A., Jin, A., Neelappa, A.: Speaker recognition using deep belief networks. [CS 229] Fall, 14 December 2012. Accessed 20 Apr 2019
  5. 5.
    Dennis, J., Dat, T.H., Li, H.: Spectrogram image feature for sound event classification in mismatched conditions. IEEE Signal Process. Lett. 18(2), 130–133 (2011)CrossRefGoogle Scholar
  6. 6.
    Neammalai, P, Phimoltares, S., Lursinsap, C.: Speech and music classification using hybrid form of spectrogram and fourier transformation. In: APSIPA (2014)Google Scholar
  7. 7.
    Nguyen, Q.T., Bui, T.D.: Speech classification using SIFT features on spectrogram images. Vietnam J. Comput. Sci. 3, 247–257 (2016)CrossRefGoogle Scholar
  8. 8.
    Radionov, A., Aliev, V., Shvets, A.A.: Deep learning approaches for understanding simple speech commands. arXiv:1810.02364v1 [cs.SD] (2018)
  9. 9.
    Saady, M.R., El-Borey, H., El-Dahshan, E.S.A., Yahia, S.: Stand-alone intelligent voice recognition system. J. Signal Inf. Process. 5(04), 70–75 (2014)Google Scholar
  10. 10.
    Bora, A., Vajpai, J., Sanjay, G.: Speaker identification for biometric access control using hybrid features. Int. J. Comput. Sci. Eng. (IJCSE) 9(11), 666–673 (2017)Google Scholar
  11. 11.
    Soleymanpour, H.M.M.: Text-independent speaker identification based on selection of the most similar feature vectors. Int. J. Speech Technol. 20, 99–108 (2017)CrossRefGoogle Scholar
  12. 12.
    Padmaja, J.N., Rao, R.R.: A comparative study of silence and non silence regions of speech signal using prosody features for emotion recognition. Indian J. Comput. Sci. Eng. (IJCSE) 7(4), 153–161 (2016)Google Scholar
  13. 13.
    Umbaugh, S.E.: Digital Image Processing and Analysis. CRC Press, London (2010)zbMATHGoogle Scholar
  14. 14.
    Makandar, A., Halalli, B.: Image enhancement techniques using highpass and lowpass filters. Int. J. Comput. Appl. 109(14), 12–15 (2015)Google Scholar
  15. 15.
    Farina, A.: Methods. Springer, Dordrecht (2014)Google Scholar
  16. 16.
    Baraa, A.K., Abdullah, N.A.Z., Abood, Q.K.: Hand written signature verification based on geometric and grid features. Iraqi J. Sci. 56(2C), 1799–1809 (2015)Google Scholar
  17. 17.
    Patel, V., Mistree, K.: A review on different image interpolation techniques for image enhancement. Int. J. Emerg. Technol. Adv. Eng. 3(12), 129–133 (2013)Google Scholar
  18. 18.
    Goshtasby, A.A.: Image Registration Principles Tools and Methods. Springer, London (2012)CrossRefGoogle Scholar
  19. 19.
    Bondarenko, A., Borisov, A.: Research on the classification ability of deep belief networks on small and medium datasets. Inf. Technol. Manag. Sci. 16, 60–65 (2013)Google Scholar
  20. 20.
    Pezeshki, M., Gholami, S.: Distinction between features extracted using deep belief networks, pp. 1–4. arXiv:1312.6157v2 [cs.LG] (2014)
  21. 21.
    English language speech database for speaker recognition (ELSDSR). Accessed 20 Mar 2019

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Suhaila N. Mohammed
    • 1
    Email author
  • Adnan J. Jabir
    • 1
  • Zaid Ali Abbas
    • 2
  1. 1.Department of Computer Science, College of ScienceUniversity of BaghdadBaghdadIraq
  2. 2.Department of Electrical and Electronic Engineering, Faculty of EngineeringUniversiti Putra MalaysiaSeri KembanganMalaysia

Personalised recommendations