Article 1317

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 technologies and metrology, Penza State University (40 Krasnaya street, Penza, Russia),
Ageykin Aleksey Viktorovich, Junior researcher, Research Institute of Fundamental and Applied Research, Penza State University (40 Krasnaya street, Penza, Russia),

Index UDK





Background. The objects of the study are patients of the Regional Mental Hospital anmed after K.R. Evgrafov with borderline mental disorders, who have fairly high percentage of false-negative diagnostic results for these diseases. The subjects of the study are algorithms for speech signals processing to diagnose borderline mental disorders. The goal is to develop an algorithm to measure the pitch frequency for systems that detect patterns of borderline mental disorders.
Materials and methods. Informative parameters of speech signals – patterns – are used as research materials. To effectively process speech signals, we use the decomposition method for empirical modes and its modification-complete MDEM with adaptive noise. The results of the study are evaluated in comparison with theknown algorithms pitch frequency measuring, and realized on the basis of: the autocorrelation function and its modifications ("YIN"), the stable method of main tone tracking (Robust Algorithm for Pitch Tracking, RAPT) and the sawtooth pitch estimate (Sawtooth Waveform Inspired Pitch Estimation, SWIPE).
Results. An algorithm for pitch frequency measuring for systems that detect patterns of borderline mental disorders has been developed. The essence of the algorithm is the decomposition of speech signals into frequency components using the adaptive method for analyzing non-stationary signals – improved complete multiple decomposition into empirical modes with adaptive noise and isolation of the component containing the fundamental tone. The article adduces a block diagram of the developed algorithm together with detailed mathematical description. The algorithm is investigated using the formed verified signal base of healthy patients and patients with psychogenic disorders of both genders aged from 18 to 60 years.
Conclusions. In accordance with the study results, the developed algorithm for measuring the fundamental tone frequency provides increased accuracy of borderline mental disorders detection: for an error of first kind, on the average, it is more accurate by 10.7 % and for a second type error – by 4.7 %.

Key words

speech signal, pattern, pitch frequency, improved complete multiple decomposition into empirical modes with adaptive noise, psychogenic disorders

Download PDF

1. Tychkov A. Yu., Ageykin A. V., Alimuradov A. K., Kalistratov V. B., Mitroshina S. Yu. Psikhicheskoe zdorov'e [Mental health]. 2017, no. 5, pp. 69–75.
2. Pantic K. M., Patras Ioannis IEEE transactions on pattern analysis and machine intelligence. 2010, vol. 32, pp. 1940–1954.
3. Bobkov A. S. Modeli i metody opredeleniya emotsional'nogo sostoyaniya cheloveka na osnove avtomatizirovannoy obrabotki i analiza videoinformatsii: dis. kand. tekhn. nauk: 05.13.01 [Human emotional condition determination methods and models on the basis of automatic videoinformation processing and analysis: dissertation to apply for the degree of the candidate of engineering sciences]. Moscow, 2013, 170p.
4. Kislova O. O. Psikhofiziologicheskie predposylki uspeshnosti raspoznavaniya emotsional'noy rechevoy ekspresii: dis. kand. biol. nauk: 03.00.13 [Psychophysical prerequisites of successful detection of emotion speech expression: dissertation to apply for the degree of the candidate of biological sciences]. Moscow, 2009, 151 p.
5. Agrafioti F. ECG in Biometric Recognition: Time Dependency and Application Challenges. Toronto, 2011.
6. Kappeler-Setz C., Gravenhorst Franz, Schumm Johannes, Arnrich Bert, Tröster Gerhard Journal Personal and Ubiquitous Computing. 2013, vol. 17, iss. 2, pp. 261–271.
7. Farwell L. A. Cogn Neurodyn. 2012, vol. 6, pp. 115–154. DOI 10.1007/s11571-012- 9192-2.
8. Quan C., Ren F. International Journal of Advanced Intelligence. 2010, vol. 2, no. 1, pp. 105–117.
9. Zaboleeva-Zotova A. V., Orlova Yu. A., Rozaliev V. L., Bobkov A. S. Materialy mezhdunarodnoy nauchno-tekhnicheskoy konferentsii OSTIS [Procedings of an International Scientific and Technical Conference OSTIS]. Minsk: BGUIR, 2012, pp. 347–350.
10. Likforman-Sulem L., Esposito A., Faundez-Zanuy M., Clémençon S., Cordasco G. IEEE Transactions on Human-Machine Systems. 2017, vol. 47, iss. 2, pp. 273–284. DOI: 10.1109/THMS.2016.2635441.
11. Barabanshchikov V. A., Zhegallo A. V. Eksperimental'naya psikhologiya [Experimental psychology]. 2014, vol. 7, no. 1, pp. 132–137.
12. Loughland C. M., Williams L. M., Gordon E. Schizophrenia Research. 2002, vol. 55, iss. 1-2, pp. 159–170.
13. Filatova N. N., Sidorov K. V. Izvestiya Yuzhnogo federal'nogo universiteta. Tekhnicheskie nauki [Proceedings of South Federal University. Engineering sciences]. 2012, no. 9 (134), pp. 39–45.
14. Davydov A. G., Kiselev V. V., Kochetkov D. S., Tkachenya A. V. Komp'yuternaya lingvistika i intellektual'nye tekhnologii: po materialam ezhegod. Mezhdunar. konf. «Dialog». Vyp. 11: v 2 t. T. 1: Osnovnaya programma konferentsii [Computer linguistics and intelligent technologies: based on proceedings of the annual International Conference “Dialogue”. Issue 11: in 2 volumes. Vol.1: Main conference program]. Moscow: Izd-vo RGGU, 2012, pp. 122–128.
15. Williamson J. R., Quatieri T. F., Helfer B. S., Ciccarelli G., Mehta D. D. Proceedings of the 4th International Workshop on Audio-Visual Emotion. Challenge, 2014, pp. 65–72.
16. Darley F. L., Aronso A. E., Brown J. R. J. Speech Lang. Hear. Res. 1969, vol. 12, pp. 47–57.
17. Dorry M. K. Emotion Identification from Spontaneous Communication: A Thesis Submitted to the Department of Computer Science in Partial Fulfilment for the Degree of Master of Science in Computer Science. Addis Ababa University College of Natural Sciences. Addis Ababa, Ethiopia, 2016, p. 93.
18. Schwenzer M., Zattarin E., Grozinger M., Mathiak K. BMC Psychiatry. 2012, vol. 12, iss. 1, pp. 32–37. 
19. Morist M. U. Emotional speech synthesis for a radio dj: corpus design and expression modeling: master thesis MTG-UPF dissertation. Barcelona, 2010.
20. Yingthawornsuk T. International Conference on Computer and Communication Technologies (ICCCT'2012), May 26–27, 2012. Phuket, 2012.
21. Yu B., Quatieri T. F., Williamson J. R., Mundt J. C. Sixteenth Annual Conference of the International Speech Communication Association. Dresden Germany, 2015, pp. 3734– 3738.
22. Grossberg S. Pattern recognition by humans and machines: Speech perception. 2013, p. 187.
23. Staudacher M., Steixner V., Griessner A., Zierhofer C. EURASIP Journal on Audio, Speech, and Music Processing. 2016, iss. 1, Dec., p. 8.
24. Kumar S., Jangra M. International Journal of Electronics & Communication Technology (IJECT). 2015, vol. 6, iss. 3.
25. Eun-Joo S., Kwang-Seok Hong International Conference on Civil, Materials and Environmental Sciences (CMES 2015). London, UK, 2015, pp. 600–603.
26. Haraa Y., Matsumotob M., Miyoshi K. Journal of Temporal Design in Architecture and the Environment. 2009, vol. 9, iss. 9, pp. 121–124.
27. Shahnaz C., Zhu W.-P., Ahmad M. O. IEEE International Symposium on Circuits and Systems (ISCAS2008), May 18–21, 2008. Seattle USA, 2008, pp. 1704–1707.
28. Klapuri A. P. IEEE Transactions on speech and audio processing. 2003, vol. 11, no. 6, Nov., pp. 804–816.
29. Cheveigne A., Kawahara H. The Journal of the Acoustical Society of America. 2002, vol. 111, no. 4, pp. 1917–1930.
30. Talkin D. Chapter 14 in Speech Coding & Synthesis. Ed. by W. B. Kleijn and K. K. Paliwan. Elsevier Science. New York USA,1995, pp. 495–518.
31. Camacho A., Harris J. G. The Journal of the Acoustical Society of America. 2008, vol. 123, no. 4, pp. 1638–1652.
32. Alimuradov A. K. International Conference on Engineering and Telecommunication (EnT), Nov. 18–19, 2015, Russia, Moscow. Moscow, 2015, pp. 77–79. DOI: 10.1109/EnT.2015.9.
33. Alimuradov A. K., Tychkov A. Yu., Ageykin A. V., Churakov P. P., Kvitka Y. S., Zaretskiy A. P. XX IEEE International Conference on Soft Computing and Measurements (SCM), May 24–26, 2017, Russia, St. Petersburg. Saint-Petersburg, 2017, pp. 610–613. DOI: 10.1109/SCM.2017.7970665.
34. Huang N. E., Zheng Sh., Steven R. L. Proc. R. Soc. Lond. 1998, vol. A454, pp. 903–995.
35. Zhaohua Wu., Huang N. E. Advances in Adaptive Data Analysis. 2009, vol. 1, no. 1, pp. 1–41.
36. Yeh J.-R., Shieh J.-S., Huang N. E. Adv. Adapt. Data Anal. 2010, vol. 2, no. 2,  pp. 135–156.
37. Torres M. E., Colominas M. A., Schlotthauer G., Flandrin P. International Conference on Acoustics, Speech and Signal Processing (ICASSP-11). Prague (CZ), 2011, pp. 4144–4147,
38. Colominasa M. A., Schlotthauera G., Torres M. E. Biomedical Signal Processing and Control. 2014, vol. 14, pp. 19–29.
39. Huang X., Acero A., Hon H.-W. Prentice Hall. New Jersey, 2001, 980 p.
40. Fant G. K. Akusticheskaya teoriya recheobrazovaniya: per. s ang. L. A. Varshavskogo i V. I. Medvedeva; nauch. red. V. S. Grigor'eva [The acoustic theory of speech production: translation from English language by L.A. Varshavskiy and V.I. Medvedev: sctientific editing by V.S. Grigoryev]. Moscow: Nauka, 1964, 284 p.
41. Popov D. I. Izvestiya vysshikh uchebnykh zavedeniy. Povolzhskiy region. Tekhnicheskie nauki [University proceedings. Volga region. Engineering sciences]. 2017, no. 1 (41), pp. 96–105.
42. Alimuradov A. K. Measurement techniques. 2017, vol. 59, no. 12, pp. 1316–1323. DOI 10.1007/s11018-016-0994-1.
43. Alimuradov A. K., Tychkov A. Yu., Frantsuzov M. V., Churakov P. P. Measurement techniques. 2015, vol. 58, iss. 9, pp. 965–969.


Дата создания: 06.02.2018 10:32
Дата обновления: 27.03.2018 14:19