Summaries of the Issue


MODELING AND SIMULATION OF COMBUSTION AND DETONATION BY SUBCRITICAL STREAMER DISCHARGE Bulat Pavel V, Esakov Igor I. , Grachev Lev P., Denissenko Petr V., Bulat Mikhail P., Volobuev Igor A.
We consider the possibilities of combustion and detonation initiation for propane mixtured with air by microwave discharges created by a quasi-optical electromagnetic beam. Comparison of initiation is performed by different types of discharge: spark, streamer, and attached one. The formation theory of streamer discharges is given, the velocity of their propagation and the volume of energy supplies are analyzed. Experiments have been carried out together with calculation of the propane-air mixture ignition by various types of discharges. It is shown that when burning is initiated by a streamer discharge, a multiple increase in the propagation velocity of the flame front and the completeness of the fuel combustion is obtained as compared to a spark discharge with an equal energy contribution. In the prechamber initiation of combustion by igniting a streamer discharge on the inner walls of the quartz tube, a significant acceleration of combustion was obtained up to the rates characteristic for the transition of deflagration to detonation. The results can be applied in the development of multi-volumetric volumetric ignition systems in internal combustion engines, gas turbine engines, low-emission combustion chambers, for combustion in supersonic flow, and in combustion chambers for detonation engines.


Предмет исследования.Представлены результаты исследования в гигагерцовом диапазоне частот диэлектрической проницаемости физиологических водных растворов и растворов глюкозы, используемых в медицинской практике. Результаты эксперимента обоснованы теоретически на основе модели Дебая–Коле (Debye–Cole). Метод. Исследования проведены на плазме крови здорового донора, воде, водных растворах NaCl (0,9%) и растворах глюкозы с концентрацией от 3 до 12 ммоль/л. Эксперименты выполнены с использованием активной методики ближнего поля (Nearfield), основанной на измерении импеданса плоской границы воздух–жидкость с помощью открытого конца коаксиального волновода в диапазоне частот 1–12 ГГц. Результаты измерений обработаны с использованием компьютерной системы векторного анализатора фирмы Rohde& Schwarz. Спектры пропускания определялись с использованием ИК-спектрометра TENZOR-Bruker. Основные результаты. Результаты моделирования показали хорошее совпадение экспериментальных результатов и модели, а также выбора основных параметров модели Debye–Coleв исследуемом диапазоне частот для всех исследуемых сред. Показано, что диапазон 3–6 ГГц может рассматриваться как основной при разработке диагностических сенсоров для безинвазивного анализа концентрации глюкозы в крови человека. Практическая значимость. Электродинамические модели тестовой жидкости, заменяющей кровь человека, позволяют промоделировать основные характеристики сенсора для качественной и количественной оценки концентрации глюкозы в крови человека и могут быть использованы при создании экспериментального образца безинвазивного глюкометра.
Subject of Research.The paper deals with temperature effects dependence of the synchronization signal parameters in an optical fiber cable for a subcarrier wave quantum communication system. Two main causes of signal distortion are considered: the change in the refractive index as a function of the average daily temperature and the dispersion effects in the optical fiber, over which the signal is transmitted in the system. Method. To account for these effects, a temperature model has been created. The signal delay is calculated as a result of external influences in the system working with a standard fiber-optic cable. Real operational conditions are taken into account, including cable laying conditions, average daily temperature and wind speed. Main Results. The simulations were carried out on the standard single-mode fiber ITU-T G.652D. It was experimentally obtained that the maximum calculated phase mismatch of the synchronization signal for a system operating at a 100 km fiber length corresponds to a 1.7 ps signal time delay. The maximum operating intervals of the system without the use of phase adjustment are calculated. The obtained results are used to improve the parameters of the subcarrier wave quantum communication system. It is determined that the change in the refractive index in the fiber causes significant distortion of the signal. It is shown that stable operation is possible with adjustment every 158 ms. The additional phase delay resulting from the dispersion effects should be adjusted every 2.3 hours. Practical Relevance. The obtained results enable to optimize the parameters of the subcarrier wave quantum key distribution system to increase the overall key generation rate.


We consider the problem of slant range distance measurement from aircrafts in conditions of complex spatial structure. The range determination in active laser range finders, including slant range, is based on measuring the time difference of two time points, the time point when the pulse exits the laser range finders, and the time point when the pulse comes back, after being reflected from a target. The signal emission reflected from a target is a variable of random process, because of the irradiated surface length, even under narrow field radiation. When determining the slant range distance from aircraft to a target, it is necessary to identify the signal emission reflected from a target, from background signal reflected by underlying surface. We propose two methods of slant range measurements, provided identification of target that is located on the underlying surface with complex structure. The first method is based on the measurement of slant range distance when the lower edge of the radiation field is aligned with the pointing direction. The second method is based on the measurement of slant range distance when the upper edge of the radiation field is aligned with the pointing direction. We propose structural schemes based on these methods and describe their operation principles. Evaluation of the advantages and disadvantages for each method is given.
The paper deals with fiber-optical cable winding methods for realization of fiber-optic communication line with high-speed object. We consider possible options of coils for optical cable winding providing mobility of one of the cable ends on an object. It is shown that the choice of a winding process is caused by the need of ensuring the minimum deformation of fiber-optical micro cable in case of separation from a winding body. It is revealed that the minimum tension value and its unevenness are observed when reeling from coils with a rocket form. Design ratios for determination of winding parameters are given. It is shown that reduction of tension unevenness reduces the jumps of internal tension and probability of break and emergence of optical signal local attenuation. Decrease in internal stresses occurs due to the absence of overlapping of the coils of the underlying layers with the overlying ones. To confirm the operability and the possibility of constructive implementation of the selected winding scheme, experiments were carried out to perform rocket and other types of winding with the use of a specially designed machine model. It is shown that the application of line rocket winding enables to achieve stability when reeling a cable during the movement and excludes breaks. Attenuation of optical signal decreases due to the increase in the bend minimum radius. This phenomenon is explained by reduction of the internal stresses causing optical signal attenuation in the place of cable separation from the coil.        
Subject of Research.A stereoscopic method of technical vision is proposed for recording the kinematic characteristics of the dynamic indentation process in determining the physico-mechanical properties of materials. The proposed method makes it possible to determine the values of the indenter motion speed with high accuracy. Method. The method is based on the use of two high-speed video cameras immovably fixed on one flat platform. Cameras allow for synchronous recording of the indentation process. The objectives and orientation of cameras in the stereo system provide intersection of the visual fields and the required depth of the image space field. Measurement of the movement speed is performed by triangulation method. The distance between the conjugate points of the recorded object on the stereo images is inversely proportional to the distance between the pair of cameras and the corresponding point of the object in the three-dimensional space. Based on the analysis of images obtained by spatially separated cameras, the coordinates of the object point are determined. Main Results. The experimental setup consisted of two high-speed monochrome camcorders Evercam 4000-32-M, rigidly fixed through stereo. Synchronous recording was kept at a speed of 4000 frames/s with a resolution of 1280 × 860 pixels. The indenter was made in the form of a steel ball with a mass of 230 g with a diameter of 38 mm and fell onto an aluminum disk 10 mm thick from a height of 310 mm. Video images from cameras were transferred to a personal computer for processing. The analysis of the obtained data was carried out in the MATLAB system with the help of a specially written software module. The sensitivity of the proposed method made it possible to determine confidently the values of the maximum approach speed of a steel ball equal to 2.39 m/s and a rebound velocity of 1.2 m/s. The random component of the method error did not exceed 2.5%. Practical Relevance. The development of this approach will enable to create high-precision sensors of dynamic indentation. The research results may be of interest to specialists involved in metrological support and non-destructive testing of materials and products in various fields of engineering and construction.
Subject of Research.The research is dedicated to the analysis of sensitivity change patterns of the cameras based on silicon CMOS-matrixes in various ambient temperatures. This information is necessary for the correct camera application for photometric measurements in-situ. The paper deals with studies of sensitivity variations of two digital cameras with different silicon CMOS matrixes in visible and near IR regions of the spectrum at temperature change. Method. Due to practical restrictions the temperature changes were recorded in separate spectral intervals important for practical use of the cameras. The experiments were carried out with the use of a climatic chamber, providing change and keeping the temperature range from minus 40 to plus 50 °C at a pitch of 10 оС. Two cameras were chosen for research: VAC-135-IP with OmniVision OV9121 matrix and VAC-248-IP with OnSemiconductor VITA2000 matrix. The two tested devices were placed in a climatic chamber at the same time and illuminated by one radiation source with a color temperature about 3000 K in order to eliminate a number of methodological errors. Main Results. The temperature dependence of the signals was shown to be linear and the matrixes sensitivities were determined. The results obtained are consistent with theoretical views, in general. The coefficients of thermal sensitivity were computed by these dependencies. It is shown that the greatest affect of temperature on the sensitivity occurs in the area (0.7–1.1) mkm. Temperature coefficients of sensitivity increase with the downward radiation wavelength increase.  The experiments carried out have shown that it is necessary to take into account the changes in temperature sensitivity of silicon matrixes in the red and near in IR regions of the spectrum. The effect reveals itself in a clearly negative way in cameras with an amplitude resolution of 10-12 bits used for aerospace and space spectrozonal photography. Practical Relevance. The obtained values of temperature sensitivity coefficients enable to correct the received signals by means of a calculation and to obtain more reliable information on the photometric properties of scenes and objects.


Subject of Research. The paper presents research results of potassium-aluminaborate glass with ferrite nanocrystals. The formation process of the ferrite nanocrystals in potassium-aluminaborate glass host is studied. The spectral characteristics of Raman scattering are analyzed. Method.The glasses under study are synthesized by the method of batch melting in the crucible. Potassium-aluminaborate glass system (K2O-Al2O3-B2O3) and such dopants as 3 wt% Fe2O3 (composition 1), 3 wt% Fe2O3 and 2 wt% MnO (composition 2) are used. The glass synthesis temperature is 1300 °C. The ferrite crystal phase nucleation occurred during heat treatment at 560 °C for 3 hours. The Raman spectra are excited by radiation of a polarized helium-neon laser (λ=633 nm) with 50 Wt power and are recorded by a single pass Renishaw spectrometer. Stimulating pulses are focused onto the sample by Leica optical microscope. Main Results. It is shown that after glass isothermal treatment at the temperature equal to 560 °C for 3 hours the formation of nanocrystals of magnetite and manganese ferrite occurs. It is connected with the appearance in the Raman spectra of additional bands near 350, 680 cm-1 and 630 cm-1, which corresponds to the modes Eg, A1g of FeFe2O4 and A1g of MnFe2O4. Practical Relevance.The activated glasses under research could be applied as the sensitive media for the design of the optical isolators based on the Faraday effect and current sensors.


Subject of Research. The paper deals with the method of adaptive synchronization in receiving devices of broadband communication systems of the hidden message exchange increasing the efficiency of computational capability usage of a receiving device. The research topicality is caused by the need in more effective usage of computing resources for accepting modules of broadband digital communication and radiolocation. Method. The proposed solution is an extension of sequential synchronization method being applied nowadays. The method consists of two synchronization stages: preliminary – hard, and subsequent – precise one. The entity of the proposed solution lies in computation of correlative function only in the area (window) near the expected central peak. The window movement along the accepted character sequence enables to find the actual peak position and to make synchronization. Decreasing of computing expenses is reached due to reduction of processed information volume. The method adaptivity is reached by exact retraining of synchronization during all communication session. The proposed solution is urgent for mobile systems of communication and radiolocation in condition of signal interference. Main Results. Simulation of synchronization system is carried out in the environment of Simulink (MATLAB). The signal created on the basis of a complex-valued matrix with the size equal to 3×4 with the special form of autocorrelation function is used as an example for synchronization. Model researches showed that the developed method enables to realize synchronization of transceiving system, without quitting the mode of the hidden (subnoise) message passing. It is shown that application of the developed method of the adaptive synchronization, gives the possibility to reduce significantly computational capability of a receiving device, necessary for synchronization. The number of operations in case of correlation function computation was decreased in 28 times as compared to a computation method in time over all range of counting and in 5 times concerning an algorithm of correlation function computation with the use of fast Fourier transform. Practical Relevance. Research results can find application in the design of receiving modules of broadband digital communication and radiolocation.
The paper presents a method of reconstruction of spatial coordinates for the point objects, located in free space, together with their number and radiation light intensity. The required information to be measured consists of the stereo images of the observed area received by the television or thermal imaging system. The image planes spatial positions are taken to be known. The method is based on the tomography approach in signal processing. For its implementation the observed space area is divided into resolution elements with known spatial coordinates. Resolution element size specifies determination accuracy of the object spatial coordinates. The suggested method makes it possible to restore a vector of optical radiation intensity distribution over the resolution elements of the observed area. This vector contains the information on the number ВОССТАНОВЛЕНИЕ ПРОСТРАНСТВЕННЫХ КООРДИНАТ ТОЧЕЧНЫХ ОБЪЕКТОВ… Научно-технический вестник информационных технологий, механики и оптики, 2017, том 17, № 4 652 and spatial coordinates of objects as well as their radiation power. Component numbers with values that exceed the background level are the numbers of resolution elements with the objects, the amount of such components is the amount of objects, while their values determine the radiation intensity. The main advantage of the method is that it does not require points identification on the images for solving the problem. No active scanners or range measured channels are required that gives the possibility for the passive object observation. The breadth of view limits of image registration systems enables to solve simultaneously both the tasks of detection and reconstruction of spatial coordinates of objects in the observed space area
Subject of Research.The considered problems are representations of the discrete equivalent description of a continuous system to a discrete description with smaller interval than the original one provided that the zero-order hold devices are used as a memory element in the digital control of continuous system. It is shown that in connection with the above, there is a problem of the signal discrepancy estimation in the task of equivalent representation of these discrete systems. Method. Estimation method of signal discrepancy relies on the capabilities of the state space framework with the use of integral representations of continuous system dynamics equation. The scalar analytical assessment of a signal discrepancy between the initial and transformed systems is created on a difference norm of vectors of stimulated system movement. Main Results. The assessment problem is solved for boundaries of the scalar value interval for signal discrepancy state vectors of the source and resulting systems. Analytical expression for this case is received, and recommendations about the equivalent system formation with a smaller discrete interval are created on its basis. Practical Relevance. The obtained theoretical results can be used in the development and analysis of MIMO discrete systems when the system has different discrete intervals of separate channels.
 Subject of Research.The paper deals with feature selection algorithms in machine learning and, particularly, in classification. А method for fast feature selection is proposed. This method combines several other feature selection methods into one linear combination (ensemble) and then optimizes their coefficients. Method. Proposed method is a priority queue based method for feature selection. It is an improvement of measure linear form (MeLiF) algorithm. This method uses priority queue for parallelization, and basically is a parallel version of the MeLiF algorithm. Main Results. Proposed and original algorithms were compared by classification quality and computation time. Comparison was performed on 36 open DNA-microarrays. It was shown that both methods had approximately the same classification quality but computation time of the new method is 4.2 to 22 times lower on a 24-core processor with 50 threads. Practical Relevance. Proposed algorithm could be used as one of the main steps in data preprocessing for high dimensional data in machine learning. Therefore, it could be used in a wide specter of classification problems on high-dimensional datasets.
 Subject of Research.We consider beamforming issues for a base station multiple antenna system in a sensor network. The feature of the considered task lies in equipment of network nodes with energy harvesters for accumulation of electromagnetic energy for a battery charge. Hence, beamforming algorithm influences  significantly on general system stability. Method. We propose a method for antenna pattern optimization that considers both characteristics of existing prototypes of harvesters and adaptive adjustment of antenna amplitude-phase components. This method is based on a reduction of the initial optimization problem to a quadratic optimization problem with consequent application of polyhedral approximation. An efficiency of the proposed approach is analyzed via simulations. Main Results. In series of computational experiments we have discovered, that an application of the considered method brings to a significant reduction of a base station transmitted electromagnetic power. Thus, for small networks (three nodes) the gain may achieve up to 4.7 dB in comparison with isotropic radiation, for large networks (thirty six nodes) it is up to 1.8 dB. Practical Relevance. The considered algorithm may be applied in development and operation support of sensor networks with nodes located statically while a constant and reliable power management is a crucial process.
The paper considers features of artificial neural networks (ANN) application for online user`s verification by handwriting dynamics. This problem is urgent due to the development of cloud computing and machine learning, that even more often are used for pattern recognition. The review of the most widespread methods of digital user`s data pre-processing shows the relevance of ANN usage for verification. On the example of discrete Fourier transformation we made the experiments with different ANN structures and training algorithms. For these purposes we used the database of Signature Verification Competition (SVC) 2004. Cartesian coordinates and time parameters of trajectories have been taken from the database. The results of research show that artificial neural networks are able to solve that task, but at the same time with increasing the number of samples for study, success probability for legal users and malefactors also increases. For increasing of ANN performance we suggest the application of correlation analysis method for research data. It helps to increase the efficiency of artificial neural network. The false acceptance rate, or FAR, is about 2.26% and the false recognition rate, or FRR, is 12.6% with the use of correlation analysis method. At the same time, the task of distinguishing between a legal user and a malefactor, knowing how the signature or the password looks, is unsolved so far. In our opinion, the problem solution lies in the usage of additional parameters of handwriting dynamics (pressure, angle of inclination) for analysis.
 We consider software of identification and assessment subsystem for condition of segmental surfaces of mass quantity of single material objects (as general population). Proposed solution supplements functionality of computer vision system (SCV) for recognition of types and sorts of objects on 2D-image. We suggest the algorithms of quantitative and qualitative assessment of each single material object condition (the element of general population) sensitive to details of their visible surface based on Pearson's criterion. Efficiency of a subsystem on different images is shown. We consider the possibilities of time reduction of video picture processing in an operating mode of computer vision system due to the decrease in computing complexity of algorithms and the increase in productivity of consecutive calculations and the organization of parallel calculations. The accuracy was calculated as the ratio of the number of correctly identified computer vision system states of the segments to their total number. It was revealed that on the images from the inspection conveyor with fruit raw materials, the SCV has an accuracy of 98.5% on the given type of objects. On the objects in the form of aspirin tablets, system of computer vision has accuracy of 93.2%, and at the objects of rice grain mass it is 95.4%.
The paper deals withthe problem of image matching in three-dimensional space using      contour description. An object-independent hierarchical structural juxtaposition algorithm is proposed. It is based on 2D structural matching algorithm using an alphabet of simple object-independent contour structural elements. This algorithm proved to be sufficiently robust and reliable for matching successfully the pictures of natural landscapes taken in differing seasons from differing aspect angles by differing sensors (the visible optical, IR, and SAR pictures, as well as the depth maps and geographical vector-type maps), but was unable to compare images of three-dimensional scenes, where it is required to apply different models of geometric transformations to different parts of the image. The three-dimensional version of the algorithm gives the possibility to overcome this limitation, but it is less robust with relation to changes in aspect angles. One of the key stages of the presented algorithm is the building of 3D scene contour descriptions. In order to increase the robustness of the algorithm a study of 3D edge detection techniques is carried out. The quantitative estimation of accuracy and speed of the presented techniques is given. The modification of the 3D structural matching algorithm based on the results of the study is proposed. The developed technique can be used for automatic navigation of extremely low flying unmanned vehicles or autonomous terrestrial robots in view of conditions with high degree a priori scene uncertainty.
Subject of Research. We propose the method for detecting an incident at face authentication when imposter tries to disguise himself as a real client. He tries to falsify the client's face by photo or video. Method. The face anti-spoofing method involves two successive steps. Obtaining facial features takes place at the first stage. Classification is performed at the second stage for making a decision if the real person or an imposter is in front of the camera. Facial features are extracted with the use of deep convolutional neural network. Classification is realized by support vector machine. One frame or a group of frames can become the input data for the method. Main Results. The proposed method for anti-spoofing gives the possibility to work with both real faces obtained with low quality and with fake faces displayed on high-resolution displays. It is confirmed by experiments on two available test datasets. Experiments show that the average value of the first and second kind errors on the test data does not exceed 9%, and the accuracy reaches values over 91%. Classification results are comparable with the best results shown when applying the other known techniques for detecting spoofing attacks on the same test bases. Practical Relevance. The proposed method can be applied to improve the quality of face authentication systems, as well as for the development of multimodal biometric systems.
The paper deals with formation and analysis of the semi-structured subject domain with the use of ontological model and  the study of fuzzy logic problems in this subject domain. The main classes and structural links of subject domain are formed, and ontology is realized in Protégé editor by hierarchical construction of entities. We give the examples of ontological model description by means of the OWL language and  describe the access technology to ontology elements through the SPARQL queries language. Basic aspects of fuzzy logic are analyzed. Advantages of fuzzy logic application in ontology creation are listed including the membership function construction with the use of fuzzy modeling tool such as Fuzzy Logic Toolbox with respect to the processunder consideration. We form fuzzy inference system that gives the possibility to estimate a degree of membership for input and output variables to the process under consideration. Ontology for planning a ship repairing process is presented as an example, particularly, sub-process of document coordination. Proposed technology makes it possible to develop and analyze models with varying degree of accuracy in conditions of uncertainty.


Subject of Research.The paper presents results of comparative testing of highly stable difference scheme with customizable dissipative properties and WENO5 scheme in the case of one-dimensional gas dynamics and mechanics of gas-suspensions problems. Method. The second order difference scheme is constructed by physical processes splitting into two phases. The first one uses the central differences with adaptive reconstruction of artificial viscosity and semi implicit approximation of the sources. TVD type reconstructions are used in the second phase. Main Results. For the representative collection of test problems, the proposed scheme has confirmed the efficiency and good quality numerical solutions at the level of the WENO5 scheme with substantially lower machine time cost. The wave structure in the decay of initial discontinuity in the non-equilibrium gas suspension and the convergence to exact self-similar solution are considered. Practical Relevance. A detailed resolution of structural peculiarities of gas flows and gas-particle mixtures allows reducing the amount of experimental development of new technologies and technical devices of coating, leakage control when using a trial particulate matter with particles of micro - and nano-sizes and other areas.
Subject of Research.The paper deals with the process of live migration for virtual machines without service interruption. We propose a model for time estimation of virtual machine  migration and service down time at live migration with "hybrid approach". Migration of virtual machines enables the applications to navigate transparently together with their execution environments between physical hosts. The migration of virtual machines without service interruption (Live Migration) is used to balance the load efficiently and optimize the deployment of virtual machines on physical nodes in data centers. Method. We have proposed a hybrid approach for live migration from the position of migration  time and service down time during the migration of virtual machines. Main Results. An analytical model is proposed that allows estimating the time of virtual machines migration and the inaccessibility of services during live migration with a hybrid approach. The migration process is analyzed with the use of a hybrid approach and compared to the other mechanisms. It is shown that the usage of hybrid approach virtual services with the same high read-write speed gives the possibility to minimize simultaneously migration time and service down time as compared to the mechanisms with copying process before stop and after it. Practical Relevance. Predicting the migration time and the inaccessibility of services is of interest in analyzing and optimizing computational processes in data centers where virtual machines can move between physical servers during preventive and emergency operations to provide intelligent load balancing. Also, the proposed models can be used to identify the possibility and feasibility of migration mechanisms incorporating into the management software products of virtualized infrastructure for various applications.
We study the physical processes occurring in electrotechnical complexes with turbo mechanisms and pipelines. The strategy for improvement of the methods and means is defined for analyzing the operating modes of electrotechnical complexes with controlled pumping stations for energy efficiency raising of their operation. Subsystem classification of such complexes is proposed; an element-wise and general analysis of the current state of their modeling is carried out. It is shown that, in spite of a large number of works devoted to this topic, a systematic approach to mathematical modeling of processes occurring in such complexes has not been developed to date. In connection with the greatest potential for energy saving of powerful complexes, the necessity of creating an effective means of their analysis is justified, particularly, in the steady-state regimes. Based on the formalized approach, a mathematical model of the generalized electrotechnical complex of the power supply system of a pumping station has been developed. The model was successfully tested in the calculation of stationary modes of power supply systems for oil pumping station and a sewerage station. It is advisable to use the proposed model for analyzing the modes of both operating and projected objects, as well as for creating automatic control systems for such objects.


The paper proposes a new experimental method for identifying of the ship hull added moment of inertia with respect to the yaw angle. A short review of the existing methods, description of the experimental stand, testing procedure, and calculation formula is given. The proposed method is based on the energy approach with special reversive symmetric motions. For implementation of the proposed method, the vessel hull is fixed in the special testing stand where an elastic element is used as the main engine. For the exact symmetry of the programmed rotating motion, the servo drive with a flywheel is installed.
The paper considers a new pausing method for intonational speech synthesis systems based on the analysis of distributional semantics in large text corpora. The support vector machine and two speech corpora in Kazakh were used for pause prediction. The prediction of pause places was carried out at the level of bigrams, where the input parameters of the bigram were the vector representations of both of its words and their bit string representation in the Brown cluster model. The carried out studies have shown that the proposed pausing method for the automatic speech synthesis systems for the Kazakh language in the narrative style provides high accuracy of pause placement. The importance of homogeneous data usage was confirmed experimentally for solving such problems. Such approach can facilitate the creation of automatic speech synthesis for many languages.
Copyright 2001-2023 ©
Scientific and Technical Journal
of Information Technologies, Mechanics and Optics.
All rights reserved.