Skip to main content
Log in

The Predicative Symptoms and Biometry of Speech Behavior

  • INFORMATION ANALYSIS
  • Published:
Automatic Documentation and Mathematical Linguistics Aims and scope

Abstract

This paper considers the issues of predicative analytics using various methods and algorithms for predicting speech based on statistical data, as well as speech recognition using neural network learning systems. It presents the probabilistic elements of text and speech behavior, which must be taken into account in creating a speech-recognition algorithm and issuing recommendations for speech improvement. A sentence analysis algorithm is proposed to convert a spoken acoustic signal into a string of symbols and words. The principles of operation of modern speech recognition systems are analyzed. A technique is proposed for processing speech phrases using mathematical algorithms with an assessment of signal levels, which makes it possible to determine the degree of influence of individual characteristics of the speech apparatus. An assessment of the severity of abnormal symptoms in subjects with speech impairments has been carried out and a method for quantitative assessment of the size of the deviation of symptoms in these subjects has been proposed.

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

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1.
Fig. 2.

Similar content being viewed by others

REFERENCES

  1. Rabiner, L.R. and Schafer, R.W., Digital Processing of Speech Signals, Prentice-Hall, 1978.

    Google Scholar 

  2. Filicheva, T.B., Cheveleva, N.A., and Chirkina, G.V., Osnovy logopedii: Ucheb. posobie (Basics of Speech Therapy: Handbook), Moscow: Prosveshchenie, 1989.

  3. Frolov A.V. and Frolov, G.V., Sintez i raspoznavanie rechi. Sovremennye resheniya (Speech Synthesis and Recognition. Modern Solutions), M.: Svyaz’, 2003.

  4. Galunov, V.I., Modern problems in the field of speech recognition. http://auditech.ru/page/darkness.html. March 12, 2016.

  5. Karpov, A.A., Kaia, Kh., and Salakh, A.A., Current problems and achievements of systems for paralinguistic speech analysis, Nauchno-Tekh. Vestn. Inf. Tekhnol. Mekh. Opt., 2016, vol. 16, no. 4, pp. 581–592.

    Google Scholar 

  6. Gorshkov, Yu.G. and Dorofeev, A.V., Commercial speech lie detectors, INFORMOST—Radioelektron. Telekommun., 2003, no. 6, pp. 13–15.

  7. Montacie, C. and Caraty, M.-J., Prosodic cues and answer type detection for the deception sub-challenge, Proceedings Interspeech-2016, San Francisco: STIH Lab.; Paris: Sorbonne Univ., 2016, pp. 2016–2020. https://doi.org/10.21437/Interspeech.2016-33

    Book  Google Scholar 

  8. Basov, O.O., Karpov, A.A., and Saitov, I.A., Metodologicheskie osnovy sinteza polimodal’nykh infokommunikatsionnykh sistem gosudarstvennogo upravleniya (Methodological Foundations for the Synthesis of Polymodal Infocommunication Systems of Public Administration), Orel: Akad. FSO RF, 2015.

  9. Butenko, Yu.I., Stroganov, Yu.V., Shevchenko, V.I., Slavnov, N.V., and Kvasnikov, A.V., A speech markup system for comparative analysis of pronunciation in different dialects, Vestn. Voronezh. Gos. Univ., Ser.: Sist. Anal. Inf. Tekhnol., 2020, no. 4, pp. 168–176. https://doi.org/10.17308/sait.2020.1/2631

  10. Slavnov, N.V., Stroganov, Y.V., and Kvasnikov, A.V., System for speech corpus development, IEEE Conference of Russian Young Researchers in Electrical and Electronic Engineering (EIConRus), 2020, pp. 1730–1732.

  11. Evseev, A.I. and Nguen, V.Kh., Research and development of a method for digital processing of a speech signal to obtain the dynamics of the format characteristics of word sounds, Vestn. Mosk. Energet. Inst., 2010, no. 4, pp. 45–49.

  12. Sidnyaev, N.I., Butenko, Yu.I., and Garazha, V.V., Statistical assessment of the associative power of meaningless letter combinations, Teor. Prikl. Lingvist., 2019, no. 5, pp. 107–124.

  13. Grachev, A.M., Linguistic approaches to automatic speech recognition, Vestn. Nizhegor. Univ. im. N. I. Lobachevskogo, 2013, no. 6-2, pp. 61–63.

  14. Magdieva, Z.Kh., Orlov, I.M., and Belenko, M.V., Features of recognition of defective speech using modern systems of automatic speech recognition, Nauchno-Tekh. Vestn. Povolzh’ya, 2019, no. 6, pp. 85–87.

  15. Sannikov, V.G., Statistical analysis of digital synthesis of a speech signal based on its autoregressive model, DSPA: Vopr. Primen. Tsifrovoi Obrab. Signalov, 2018, vol. 8, no. 2, pp. 171–176.

    Google Scholar 

  16. Petrova, E.M. and Nichushkina, T.N., Analysis of problems of automatic recognition of Russian speech, Tekhnol. Inzh. Inf. Sist., 2019, no. 1, pp. 3–10.

  17. Kukhtinova, M.S., Pozolotina, N.A., and Trubin, V.G., Speech recognition systems, Avtom. Program. Inzh., 2014, no. 2, pp. 47–49.

  18. Tampel', I.B., Automatic speech recognition: Main stages in 50 years, Nauchno-Tekh. Vestn. Inf. Tekhnol. Mekh. Opt., 2015, vol. 15, no. 6, pp. 957–968.

    Google Scholar 

  19. Budkov, V.Yu., Savel’ev, A.I., and Vol’f, D.A., Methods for studying the parameters of a speech signal, reflecting the validity of the transmitted information, Dokl. TUSUR, 2016, vol. 19, no. 2, pp. 56–60.

    Article  Google Scholar 

  20. Babarinov, S.L. and Budnikova, M.A., On speech recognition, Nauchn. Vedomosti Belgorod. Gos. Univ., Ser.: Ekon., Inf., 2014, no. 21, pp. 182–185.

Download references

Author information

Authors and Affiliations

Authors

Corresponding authors

Correspondence to N. I. Sidnyaev, Yu. I. Butenko, Yu. V. Stroganov or A. D. Kiseleva.

Ethics declarations

The authors declare that they have no conflicts of interest.

Additional information

Translated by L. Solovyova

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Sidnyaev, N.I., Butenko, Y.I., Stroganov, Y.V. et al. The Predicative Symptoms and Biometry of Speech Behavior. Autom. Doc. Math. Linguist. 55, 26–37 (2021). https://doi.org/10.3103/S0005105521010064

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.3103/S0005105521010064

Keywords:

Navigation