Advertisement

Speaker Verification Method Using HTM for Security System

  • Yuki SakaguchiEmail author
  • Rin Hirakawa
  • Hideki Kawano
  • Kenichi Nakashi
  • Yoshihisa Nakatoh
Conference paper
  • 277 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1253)

Abstract

In recent years, we have been using biometric verification systems in various places such as daily life and businesses. However, it’s insufficient in hospital and food factory to introduction of the security system of the room access control. This is because they wear gloves, masks and hats in hospitals and factories, so they cannot verify faces or fingerprints. In this study, we propose a speaker verification system using HTM (Hierarchical Temporal Memory). We verify speaker and detection of unlearned speakers by experiments. In addition, we consider the use in hospitals and factories, and also evaluate it in a noisy environment. The evaluation values are Precision, Recall, and F-measure. The experimental results show that in the case of 10 learners, F-measure exceeded 0.6 in the classification of 2 classes of learners and non-learners.

Keywords

Security system Speaker verification Voice authentication HTM 

References

  1. 1.
  2. 2.
    Numenta, Inc, altalk K.K.: Hierarchical Temporal Memory including HTM Cortical Learning Algorithms (2010)Google Scholar
  3. 3.
    James, M., Ernest, F., Dhireesha, K.: IEEE: a mathematical formalization of hierarchical temporal memory’s spatial pooler (2016)Google Scholar
  4. 4.
    Xi, C., Wei, W., Wei, L: An overview of hierarchical temporal memory: a new neocortex algorithm (2012)Google Scholar
  5. 5.
    Hiroki, U.: A study on comparison of speaker verification methods using various machine learning, pp. 38–39 (2019)Google Scholar
  6. 6.
    Jeff, H, Sandra, B, Ito, F.: thinking brain thinking computer, pp. 53–54. Random House Ltd., New York (2005)Google Scholar
  7. 7.
  8. 8.
    Kong, A.L., Anthony, L., Guangsen, W., Patrick, K., Niko, B., David, V.L., Hagai, A., Marcel, K., Carlos, V., Bin, M., Haizhou, L., Themos, S., Jahangir, A., Albert, S., Javier, P.: The RedDots data collection for speaker recognition (2015)Google Scholar
  9. 9.
    Hossein, Z., Lukas, B., Hossein, S., Jan, H.C.: Spoken Pass-phrase Verification in the i-vector Space (2018)Google Scholar

Copyright information

© The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG 2021

Authors and Affiliations

  • Yuki Sakaguchi
    • 1
    Email author
  • Rin Hirakawa
    • 1
  • Hideki Kawano
    • 1
  • Kenichi Nakashi
    • 1
  • Yoshihisa Nakatoh
    • 1
  1. 1.Kyushu Institute of TechnologyFukuokaJapan

Personalised recommendations