| Authors |
Alimuradov Alan Kazanferovich, candidate of technical sciences, director of student research and production business incubator, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: alansapfir@yandex.ru
Tychkov Aleksandr Yur'evich, candidate of technical sciences, deputy director at the Research Institute for Basic and Applied Studies, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: tychkov-a@mail.ru
Churakov Petr Pavlovich, doctor of technical sciences, professor, sub-department of information and measuring equipment and metrology, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: churakov-pp@mail.ru
Sultanov Boris Vladimirovich, doctor of technical sciences, professor, sub-department of information security systems and technologies, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: ibst@pnzgu.ru
|
| Abstract |
Background. At present, various methods based on analysis of facial expressions and gesticulation, parameters of physiological activity of the organism, blood biochemical parameters, parameters of text handwriting and keyboarding, oculography, etc. are used to assess psycho-emotional state. Methods based on speech analysis are the most adaptive. The purpose of the work is to develop a method for determining formant intelligibility of speech to increase the assessment efficiency of psycho-emotional state of control system operators with a high degree of responsibility.
Materials and methods. A unique technology for adaptive decomposition of non-stationary signals, namely, the improved complete ensemble empirical mode decomposition with adaptive noise, and formant analysis were used in the development of the method. Software implementation of the method was performed in the mathematical modeling environment © Matlab (MathWorks).
Results. A method for assessing psychoemotional state, applicable to control system operators with a high degree of responsibility, has been developed. The nature of the method consists in adaptive decomposition of a speech signal into frequency bands of equal articulation, using the improved complete ensemble empirical mode decomposition with adaptive noise, and determining formant intelligibility, as well as frequency, width, level and quality factor of formant regions in these bands using formant analysis. A mathematical description of the decomposition and a simplified block diagram for the proposed method are briefly presented. A study of the method was conducted using a formed base of phonetically balanced speech signals recorded in healthy people and people with psycho-emotional disorders.
Conclusions. In accordance with the research results, the developed method provides high determination accuracy of psycho-emotional disorders (the first kind error is 8.16 %, the second kind error is 5.66 %), and can be successfully tested to assess psychoemotional state of control system operators with a high degree of responsibility.
|
| Key words |
speech signal, improved complete ensemble empirical mode decomposition with adaptive noise, formant intelligibility, format analysis, psycho-emotional disorder
|
