Skip to main content
SpringerLink
Log in

Method for Measuring the Intelligibility of Speech Signals in the Kullback–Leibler Information Metric

  • Published:
Measurement Techniques Aims and scope

We consider the problem of determination of the intelligibility of speech of a speaker according to a finite fragment of the speech signal. It is shown that the main difficulties in the solution of this problem are connected with the necessity of analysis of small samples. To overcome the problem of small samples, we proposed a new high-speed method for measuring the intelligibility of speech signals on the sonic level of its perception. The proposed method is based on the information indicator of speech intelligibility in the Kullback-Leibler metric. We consider an example of practical realization of the new method with the use of a self-regression model of minimum sound units from the speech flow of a speaker. The characteristics of efficiency of the new method are analyzed. It is shown that, under certain conditions, the application of the information indicator enables us to realize the general systems principle of guaranteed result. On the basis of the software developed by the authors, we designed and performed full-scale experiments and established quantitative estimates for the speed of this method. It is shown that, with the help of this method, quite accurate and reliable estimates of the information indicator are obtained for short (2–3 min) segments of speech signals. The accumulated results and the conclusions made on their basis are intended for applications in the development of new systems and improvement of the existing systems of automatic speech processing and recognition intended for the operation in the real-time mode.

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

Access this article

Log in via an institution

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

Instant access to the full article PDF.

Institutional subscriptions

Fig. 3.
Fig. 1.
Fig. 2.

Similar content being viewed by others

References

  1. V. V. Savchenko, “A method of measuring the index of acoustic voice quality based on an information-theoretic approach,”Izmer. Tekhn., No. 1, 60–64 (2018), DOI: https://doi.org/10.35446/0368-1025it.2018-1-60-64.

  2. V. V. Savchenko, “Itakura–Saito divergence as an element of the information theory of speech perception,” J. Comm.Technol. Electron., 64, No. 6, 590–596 (2019), DOI: https://doi.org/10.1134/S1064226919060093.

    Article  Google Scholar 

  3. K. Wang, P. Wang, and X. Qiu, “Increasing speech intelligibility in monaural hearing by adding noise at the otherear,” Appl. Acoust., 146, 50–55 (2019), DOI: https://doi.org/10.1016/j.apacoust.2018.10.035.

    Article  Google Scholar 

  4. E. Hossain, M. Zilany, and E. Davies-Venn, “On the feasibility of using a bispectral measure as a nonintrusive predictorof speech intelligibility,” Comput. Speech Lang., 57, 59–80 (2019), DOI: https://doi.org/10.1016/j.csl.2019.02.003

    Article  Google Scholar 

  5. T. A. Margaryan and O. A. Voinov, “Analysis of methods aimed at the evaluation of speech intelligibility,” in: Microelectronics and Informatics, S. A. Gavrilov (ed.), NIU MIET, Moscow (2018), pp. 143–148.

    Google Scholar 

  6. E. V. Shatalov, S. V. Popov, and N. A. Dubovitskii, “Method for evaluating the clarity of speech received through the channel of intercommunication devices of self-contained respirators,” Izmer. Tekhn., No. 6, 61–63 (2004).

  7. D. P. Linde (ed.), Handbook on Radioelectronic Devices, Energiya, Moscow (1978), Vol. 2.

  8. V. V. Savchenko and A. V. Savchenko, “Criterion of significance level for the selection of the order of spectral estimation of entropy maximum,” Radioelectron. Communic. Syst., 62, No. 5, 223–231 (2019), DOI: 10.3103%2FS073 5272719050042.

  9. P. A. Kir’yanov and A. Sh. Kaganov, “Evaluation of the stability of formant ratios in the spectral analysis of speechsignals,” Sudebn. Med., 4, No. S1, 152–153 (2018), DOI: https://doi.org/10.19048/2411-8729-2018-4-1s.

    Article  Google Scholar 

  10. A. A. Borovkov, Mathematical Statistics, Lan’, St. Petersburg (2010).

    Google Scholar 

  11. А. V. Savchenko and V. V. Savchenko, “A method for measuring the pitch frequency of speech signals for the systems of acoustic speech analysis,” Izmer. Tekhn., No. 3, 59–63 (2019), DOI: https://doi.org/10.32446/0368-1025it.2019-3-59-63.

  12. A. A. Konev, R. V. Meshcheryakov, and I. A. Khodashinskii, “Recognition of vowel sounds according to the information about the first and second harmonics,” in: Analysis of Spoken Russian: 6th Interdiscipl. Workshop, SPbGU, St. Petersburg (2012).

  13. V. V. Savchenko, “Solution of the problem of multiple comparisons encountered in the problems of automatic signal recognition at the output of the voice communication channel,” Elektrosvyaz, No. 12, 22–27 (2017).

  14. S. L. Marple, Digital Spectral Analysis, Prentice Hall, Englewood Cliffs, NJ (1987).

    Google Scholar 

  15. Voice Self-Analysis Software Package, https://sites.google.com/site/frompldcreators/VSAUserGuideV1.pdf, acc.04.19.2018.

Download references

Author information

Authors and Affiliations

  1. Nizhnii Novgorod State Linguistic University, Nizhnii Novgorod, Russia

    V. V. Savchenko

  2. National Research University Higher School of Economics, Nizhnii Novgorod, Russia

    L. V. Savchenko

Authors
  1. V. V. Savchenko
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. L. V. Savchenko
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to V. V. Savchenko.

Additional information

Translated from Izmeritel’naya Tekhnika, No. 9, pp. 59–64, September, 2019.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Savchenko, V.V., Savchenko, L.V. Method for Measuring the Intelligibility of Speech Signals in the Kullback–Leibler Information Metric. Meas Tech 62, 832–839 (2019). https://doi.org/10.1007/s11018-019-01702-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11018-019-01702-1

Keywords

Search

Navigation