Article 7317

Title of the article



Alimuradov Alan Kazanferovich, Candidate of engineering sciences, Director of the Student Research and Production Business-Incubator, Penza State University (40 Krasnaya street, Penza, Russia),
Tychkov Aleksandr Yur'evich, Candidate of engineering sciences, deputy director, Research Institute of Fundamental and Applied Research, Penza State University (40 Krasnaya street, Penza, Russia),
Churakov Petr Pavlovich, Doctor of engineering sciences, professor, sub-department of information measuring technology and metrology, Penza State University (40 Krasnaya street, Penza, Russia),
Torgashin Sergey Ivanovich, Candidate of engineering sciences, head of sub-department of rocket-space and aircraft instrument engineering, Penza State University (40 Krasnaya street, Penza, Russia),

Index UDK





Background. The low accuracy of recognition of speech commands is one of the main problems in practical implementation of systems for assessing psychogenic states. This is due to the use non-adaptive methods unstable to noise for processing complex speech signals. The article proposes a method of signal / pause segmentation to work in a noisy environment.
Materials and methods. In the development of the method we used: the method of adaptive processing of speech signals – complementary multiple decomposition into empirical modes (KMDE) and the method of differentiation based on the physiological aspect of speech formation and human hearing apparatus’ functional. 
Results. The article presents a block diagram of the method with detailed mathematical description. The advantages are shown in comparison with the known signaling / pause signaling / STE + ZCR, IE and MFCC.
Conclusions. The developed method provides an increase in the coefficient of actual detection by an average of 6%. A comparison of the study results allows us to conclude that the developed signal / pause segmentation method is recommended for practical application in psychogenic states assessment systems. 

Key words

processing of speech signals, signal/pause segmentation, speech recognition, voice control system, complementary multiple decomposition method

Download PDF

1. Bachu R. G., Kopparthi S., Adapa B., Barkana B. D. American Society for Engineering Education (ASEE) Zone Conference Proceedings. Pittsburgh, USA, 2008, pp. 1–7.
2. Moattar M. H., Homayounpour M. M. EUSIPCO-2009: 17-th European Signal Processing Conference, Glasgow, Scotland, August 24–28, 2009. Glasgow, Scotland, 2009, pp. 2549–2553.
3. Huaping L., Xin Li J. System Simulation. 2008, pp. 51–59.
4. Mattias N. Sound and Image Processing Laboratory School of Electrical Engineering KTH (Royal Institute of Technology). Stockholm, 2006, 54 p.
5. Ma Jingxia Research on Noisy Voice Activity Detection Method [D]. Yanshan: Yanshan University, 2007.
6. Jancovic P., Kokuer M. IEEE Signal Processing Letters. 2006, vol. 14, iss. 1, pp. 66– 69.
7. Ahmadi S., Spanias A. S. IEEE Transactions on Speech and Audio Processing. 2002, vol. 7, iss. 3, pp. 333–338.
8. Shah J. K., Shah J. K., Iyer A. N., Smolenski B. Y., Yantorno R. E. IEEE International Conference on Acoustics, Speech, and Signal Processin. Philadelphia, 2004, pp. 17–21.
9. Saha G. A, Sandipan Ch., Suman S. Proceedings of the NCC 2005. 2005, Jan., p. 5. 10. Rahman M. S., Shimamura T. Eleventh Annual Conference of the International Speech Communication Association. Makuhar, 2010, pp. 653–656.
11. Juang C. F., Cheng Chun Nan Expert Systems with Applications. 2009, vol. 1, pp. 321– 332.
12. Alimuradov A. K., Tychkov A. Yu., Churakov P. P., Kvitka Yu. S., Zaretskiy A. P., Vishnevskaya G. V. 2016 International Conference on Engineering and Telecommunication (EnT), Nov. 29–30, 2016. Moscow, Russia, 2016, pp. 3–6. DOI: 10.1109/EnT.2016.009.
13. Yeh J.-R., Shieh J.-S., Huang N. E. Advances in Adaptive Data Analysis. 2010, vol. 2, no. 2, pp. 135–156. DOI: 10.1142/S1793536910000422.
14. Sarma V., Venugopal D. ICASSP '78. IEEE International Conference on Acoustics, Speech, and Signal Processing. 1978, vol. 3, Apr., pp. 1–4.
15. Alimuradov A. K., Churakov P. P., Tychkov A. Yu., Artemov I. I., Kuzmin A. V. International Siberian Conference on Control and Communications (SIBCON 2016), May 12–14, 2016 [ ]. Moscow, Russia, 2016, p. 6. DOI: 10.1109/SIBCON.2016.7491754.
16. Alimuradov A. K., Murtazov F. Sh. Measurement techniques. 2016, vol. 58, iss. 10, pp. 1107–1112. DOI 10.1007/s11018-015-0850-8.
17. Tychkov A. Yu., Alimuradov A. K., Frantsuzov M. V., Churakov P. P. Measurement techniques. 2015, vol. 58, iss. 9, pp. 965–969. DOI 10.1007/s11018-015-0826-8.
18. Popov D. I. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki [University proceedings. Volga region. Engineering sciences]. 2017, no. 1 (41), pp. 96–105.
19. Rabiner L. R., Shafer R. V. Tsifrovaya obrabotka rechevykh signalov: per. s angl. [Digital speech signal protection: translation from English]. Moscow: Radio i svyaz', 1981, 496 p.
20. Kuleshov A., Zaretskiy A., Ilyin A., Poteryakhina A., Poteryakhin A. Iranian Hear Journal. 2015, vol. 16, no. 2, pp. 41–53.


Дата создания: 06.02.2018 10:36
Дата обновления: 26.02.2018 15:51