Open AccessModels and a Tecnique for Determining the Speech Activity of a User of a Socio-Cyberphysical System
Author(s) -
Elizaveta Usina,
Aleksandra Shabanova,
Igor Lebedev
Publication year - 2020
Publication title -
izvestiâ ûgo-zapadnogo gosudarstvennogo universiteta
Language(s) - English
Resource type - Journals
eISSN - 2686-6757
pISSN - 2223-1560
DOI - 10.21869/2223-1560-2019-23-6-225-240
Subject(s) - computer science , signal (programming language) , process (computing) , speech recognition , quality (philosophy) , set (abstract data type) , noise (video) , voice activity detection , real time computing , speech processing , acoustics , artificial intelligence , philosophy , epistemology , image (mathematics) , programming language , operating system , physics
Purpose of reseach. The article presents the development of the model-algorithmic support for the process of determining the speech activity of a user of a socio-cyberphysical system. A topological model of a distributed subsystem of audio recordings implemented in limited physical spaces (rooms) is proposed; the model makes it possible to assess the quality of perceived audio signals for the case of distribution of microphones in such a room. Based on this model, a technique for determining the speech activity of a user of a socio-cyberphysical system, which maximizes the quality of perceived audio signals when a user moves in a room by means of determining the installation coordinates of microphones has been developed. Methods. The mathematical tools of graph theory and set theory was used for the most complete analysis and formal description of the distributed subsystem of the audiorecording. In order to determine the coordinates of the placement of microphones in one room, a relevant technique was developed; it involves performing such operations as emitting a speech signal in a room using acoustic equipment and measuring signal levels using a noise meter in the places intended for installing microphones. Results. The dependences of the correlation coefficient of the combined signal and the initial test signal on the distance to the signal source were calculated for a different number of microphones. The obtained dependences allow us to determine the minimum required number of spaced microphones to ensure high-quality recording of the user’s speech. The results of testing the developed technique for determining speech activity in a particular room indicate the possibility and high efficiency of determining the speech activity of a user of a socio-cyberphysical system. Conclusion. Application of the proposed technique for determining the speech activity of a user of a sociocyberphysical system will improve the recording quality of the audio signal and, as a consequence, its subsequent processing, taking into account the possible movement of a user.