Search

This article presents approaches, methods, and algorithms for the intellectualization of existing systems and development of fundamentally new systems of transformation of information into forms convenient for human perception. Interfaces with computer environments are proposed for text, voice, and visual ways of communication and their interaction. Information technologies are developed to create tools for training people with hearing impairments, communication with people with disabilities, in medicine, etc.

The article considers the information model of semantic structure of informational education material and the corresponding information technology for creation of semantic structure of educational materials. The formal representation of the semantic structure of such informational education materials includes the set of headings, the set of terms, the set of words and the set of relations. The set of relations includes elements of the semantic structure of the informational education materials, which determine the presence and character of relations between other elements of the semantic structure of the informational education materials. The set of relations include relations between headings, relations between headings and key terms, relations between key terms and words. This information model is the formal representation of semantic structure of informational education material of the course of discipline, and in the given form it allows to use it as the model for implementation of the corresponding information technology. The established effectiveness of the proposed technology allows use it to solution a number of urgent tasks, such as semantic assistance in creating tests, determination the conformity of educational materials to content requirements, determination the conformity of sets of test tasks to educational materials, etc.

The authors present new results in solving problems of concatenative segment synthesis of voice information with prosody and vocal utterance, computer modeling of human voice signals based on joint models of human voice source and vocal tract, and speech signal preprocessing for automated documenting systems. The experiments show the efficiency of the proposed approaches.

The characteristic forms of facial expressions of the emotional states of a person are typical of a rather large degree of generalization on the basis of common physiological structures and the location of the muscles that form the human face. This circumstance is one of the main reasons for the commonality of human manifestations of emotions that are reflected in the face. By the nature and form of facial expressions on the face with high probability, it is possible to determine the emotional state of a person with some correction on the part of the cultural characteristics and traditions of certain groups. In accordance with the existence of common mimic forms of emotional manifestations, an approach is proposed to create a model of recognition of emotional manifestations on the face of a person with relatively low requirements for the means of photo, video-fixation and acceptable speed in the video stream. The creation of the model is based on the implementation of the hyperplane classification of mimic manifestations of major emotional states. One of the main advantages of the proposed approach is the small computational complexity that allows realizing the recognition of the changes in people’s emotional state without any special equipment (for low-resolution or long-distance video cameras). In addition, the model developed on the basis of the proposed approach allows obtaining proper recognition accuracy with low requirements for quality image characteristics, which allows extending the scope of practical application to a great extent. One example of practical application is control over the drivers in the process of driving the vehicle, complex production operators, and other automated visual surveillance systems. The set of detected emotional states is formed in accordance with the set tasks and gives the opportunity to focus on the recognition of mimic forms and group characteristic structural manifestations based on the set of distinguished characteristic features. Problems in programming 2020; 2-3: 173-181