Neuron-Like Approach to Speech Recognition

Abstract

In this paper, we present a new approach to speech recognition based on A. Zhdanov’s biomorphic neuron-like networks, which is also known as the autonomous adaptive control (AAC) method. In contrast to artificial neural networks (ANNs), a neuron in the AAC method is itself a self-learning pattern recognition system. We attempt to build a speech recognition system as a construction of such neurons without a program component. If this attempt is successful, then we will be able to simulate the natural principle of speech recognition not only in a program way but also via parallel hardware implementations. We understand the speech recognition problem as one of the speech processes in natural nervous systems that is to be simulated.

This is a preview of subscription content, log in to check access.

References

  1. 1.

    Zhdanov, A.A., Avtonomnyi iskusstvennyi intellekt (Autonomous Artificial Intelligence), Moscow: Binom. Laboratoriya znanii, 2008.

    Google Scholar 

  2. 2.

    Zhdanov, A.A., On the concept of autonomous artificial intelligence, in Iskusstvennyi intellekt v tekhnicheskikh sistemakh (Artificial Intelligence in Technical Systems), Moscow: Gos. Inst. Fiz. Tekh. Probl., 1997, pp. 142–157

    Google Scholar 

  3. 3.

    Zhdanov, A.A. and Naumkina, T.S., Modeling of language phenomena in neuron-like control systems, Sb. nauchn. tr. Vserossiiskoi nauchno-tekhnicheskoi konferentsii Neiroinformatika-2007 (Proc. All-Russ. Sci.-Tech. Conf. Neuroinformatics-2007), part 3, pp. 76–84.

  4. 4.

    Zhdanov, A., Kondukov, A., Naumkina, T., and Dmitrienko, O., Automatic origin of a language in AAC neuron-like systems, Proc. 11th Int. Conf. Speech and Computer (SPECOM), 2006, pp. 550–554

    Google Scholar 

  5. 5.

    Zhdanov, A.A. and Naumkina, T.S., Modeling of formation of extralinguistic factors influencing the attitude of the recipient towards language messages, Proc. 12th Int. Conf. Speech and Computer (SPECOM), 2007, pp. 833–838

    Google Scholar 

  6. 6.

    Nussbaumer, H.J., Fast Fourier Transform and Convolution Algorithms, Springer, 1982.

    Google Scholar 

  7. 7.

    Neiman, L.V., Bogomil’skii, M.R., and Seliverstov, V.I., Anatomiya, fiziologiya i patologiya organov slukha i rechi (Anatomy, Physiology, and Pathology of the Organs of Hearing and Speech), Moscow: Vlados, 2001.

    Google Scholar 

  8. 8.

    Lindasalwa, M., Begam, M., and Elamvazuthi, I., Voice recognition algorithms using Mel frequency cepstral coefficient (MFCC) and dynamic time warping (DTW) techniques, 2010, Preprint no. 1003.4083.

    Google Scholar 

  9. 9.

    Zhdanov, A.A., Kryzhanovskii, M.V., and Preobrazhenskii, N.B., Bionic adaptive intelligent control system for a mobile robot, Iskusstvennyi Intellekt, 2002, vol. 4, pp. 341–350.

    Google Scholar 

  10. 10.

    Gefke, D.A. and Zatsepin, P.M., Application of hidden Markov models to recognition of sound sequences, Izv. Altaisk. Gos. Univ., 2012, nos. 1–2, pp. 72–76.

    Google Scholar 

  11. 11.

    Campbell, W.M., et al., Support vector machines for speaker and language recognition, Comput. Speech Lang., 2006, vol. 20, pp. 210–229.

    Article  Google Scholar 

  12. 12.

    Haykin, S., Neural Networks: A Comprehensive Foundation, Prentice Hall, 1998, 2nd ed.

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to N. N. Diep.

Additional information

Original Russian Text © N.N. Diep, A.A. Zhdanov, 2018, published in Programmirovanie, 2018, Vol. 44, No. 3.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Diep, N.N., Zhdanov, A.A. Neuron-Like Approach to Speech Recognition. Program Comput Soft 44, 170–180 (2018). https://doi.org/10.1134/S0361768818030088

Download citation