Raziyam Anayatova - Academia.edu (original) (raw)
Uploads
Papers by Raziyam Anayatova
Dinamika sistem, mehanizmov i mašin, 2020
В данной статье рассматривается проблема разработки эффективного метода автоматической классифика... more В данной статье рассматривается проблема разработки эффективного метода автоматической классификации эмоций авиационного персонала (диктора) по голосу. Для этого решается задача по созданию дикторонезависимого алгоритма, способного выполнять многоклассовую классификацию семи эмоциональных состояний человека (радость, страх, гнев, печаль, отвращение, удивление и нейтральное состояние) на основании набора из 48 информативных признаков. Данные признаки формируются из цифровой записи речевого сигнала путем расчета мел-частотных кепстральных коэффициентов и частоты основного тона для отдельных фреймов звукозаписи. Повышение информативности и снижение размерности для мел-частотных кепстральных коэффициентов выполняется за счет их обработки при помощи глубокой сверточной нейронной сети. Модель классификатора реализована при помощи логистической регрессии, которая обучалась по указанным информативным признакам на базе записей эмоционально окрашенных образцов английской речи. В результате обучения на тестовой выборке доля правильных ответов распознавания составляет accuracy = 0,96. Предложенное в работе решение может быть использовано для улучшения человеко-машинных интерфейсов, а также в области авиационных перевозок, медицине, маркетинге и пр.
ASJ, 2021
The article considers topical issues of the introduction of the discipline "Academic Writing... more The article considers topical issues of the introduction of the discipline "Academic Writing" in the conditions of modernization of higher education in Kazakhstan. The necessity of its widespread introduction into the Kazakhstani education system as a subject has been substantiated. It is noted that it affects the quality of professional training of students, undergraduates and doctoral students and makes a significant contribution to the competitiveness of Kazakhstani education and science.
Journal of Physics: Conference Series, 2021
This article addresses the problem of developing an effective method for automatically classifyin... more This article addresses the problem of developing an effective method for automatically classifying the aviation personnel emotions (announcer) by voice. To this end, it is possible to create a dictatorial independent algorithm capable of performing a multi-grade classification of the seven emotional states of a person (joy, fear, anger, sadness, disgust, surprise and neutrality) on the basis of a set of 48 informative features. These features are formed from the digital recording of the speech signal by calculating Mel Frequency Cepstral coefficient and the main tone frequency for individual recording frames. The increase of informativeness and the reduction of the dimension for the Mel Frequency Cepstral coefficient is achieved by processing said coefficients with the aid of a deep, convergent neural network. The model of the classifier is realized by means of logistic regression, which was trained on the basis of emotionally colored English speech samples by these informative feat...
Bulletin of the National Engineering Academy of the Republic of Kazakhstan, 2020
A method foraircraft engine state assessment is described, based on the theory of identification ... more A method foraircraft engine state assessment is described, based on the theory of identification measurements and consisting in the analysis of the regularity properties of the temporal and correlation functions of the vibration signal. An example of an aircraft engine dynamics analysis during flight tests is considered. Four classes of states are distinguished according to the “norm – defect” scale.
Transport and Telecommunication Journal, 2021
This paper proposes a method of automatic speaker-independent recognition of human psycho-emotion... more This paper proposes a method of automatic speaker-independent recognition of human psycho-emotional states by analyzing the speech signal based on Deep Learning technology to solve the problems of aviation profiling. For this purpose, an algorithm to classify seven human psycho-emotional states, including anger, joy, fear, surprise, disgust, sadness, and neutral state was developed. The algorithm is based on the use of Mel-frequency cepstral coefficients and Mel spectrograms as informative features of speech signals audio recordings. These informative features are used to train two deep convolutional neural networks on the generated dataset. The developed classifier testing on a delayed verification dataset showed that the metric for the multiclass fraction of correct answers’ accuracy is 0.93. The solution proposed in the paper can be in demand in human-machine interfaces creation, medicine, marketing, and in the field of air transportation.
Handbook of Pre-Clinical Continuous Intravenous Infusion, 2000
Proceedings of Computer Graphics International 2018 on - CGI 2018, 2018
The Visual Computer, 2018
Journal of Advanced Research in Law and Economics, 2019
The relevance of the study is due to the fact that not a single sovereign country agrees to allow... more The relevance of the study is due to the fact that not a single sovereign country agrees to allow uncontrolled commercial activity of foreign airlines on its territory. Hence the need for a clear international legal regulation of the rights to carry out such commercial activities. In this context, the article aims to analyze the main forms and methods of commercial activity. Leading approach to the study of this problem is the descriptive method that has afforded revealing peculiarities of terms of commercial agreements and proposed air fares. The materials of the paper imply the practical significance for the university teachers of the economic and legal specializations.
Dinamika sistem, mehanizmov i mašin, 2020
В данной статье рассматривается проблема разработки эффективного метода автоматической классифика... more В данной статье рассматривается проблема разработки эффективного метода автоматической классификации эмоций авиационного персонала (диктора) по голосу. Для этого решается задача по созданию дикторонезависимого алгоритма, способного выполнять многоклассовую классификацию семи эмоциональных состояний человека (радость, страх, гнев, печаль, отвращение, удивление и нейтральное состояние) на основании набора из 48 информативных признаков. Данные признаки формируются из цифровой записи речевого сигнала путем расчета мел-частотных кепстральных коэффициентов и частоты основного тона для отдельных фреймов звукозаписи. Повышение информативности и снижение размерности для мел-частотных кепстральных коэффициентов выполняется за счет их обработки при помощи глубокой сверточной нейронной сети. Модель классификатора реализована при помощи логистической регрессии, которая обучалась по указанным информативным признакам на базе записей эмоционально окрашенных образцов английской речи. В результате обучения на тестовой выборке доля правильных ответов распознавания составляет accuracy = 0,96. Предложенное в работе решение может быть использовано для улучшения человеко-машинных интерфейсов, а также в области авиационных перевозок, медицине, маркетинге и пр.
ASJ, 2021
The article considers topical issues of the introduction of the discipline "Academic Writing... more The article considers topical issues of the introduction of the discipline "Academic Writing" in the conditions of modernization of higher education in Kazakhstan. The necessity of its widespread introduction into the Kazakhstani education system as a subject has been substantiated. It is noted that it affects the quality of professional training of students, undergraduates and doctoral students and makes a significant contribution to the competitiveness of Kazakhstani education and science.
Journal of Physics: Conference Series, 2021
This article addresses the problem of developing an effective method for automatically classifyin... more This article addresses the problem of developing an effective method for automatically classifying the aviation personnel emotions (announcer) by voice. To this end, it is possible to create a dictatorial independent algorithm capable of performing a multi-grade classification of the seven emotional states of a person (joy, fear, anger, sadness, disgust, surprise and neutrality) on the basis of a set of 48 informative features. These features are formed from the digital recording of the speech signal by calculating Mel Frequency Cepstral coefficient and the main tone frequency for individual recording frames. The increase of informativeness and the reduction of the dimension for the Mel Frequency Cepstral coefficient is achieved by processing said coefficients with the aid of a deep, convergent neural network. The model of the classifier is realized by means of logistic regression, which was trained on the basis of emotionally colored English speech samples by these informative feat...
Bulletin of the National Engineering Academy of the Republic of Kazakhstan, 2020
A method foraircraft engine state assessment is described, based on the theory of identification ... more A method foraircraft engine state assessment is described, based on the theory of identification measurements and consisting in the analysis of the regularity properties of the temporal and correlation functions of the vibration signal. An example of an aircraft engine dynamics analysis during flight tests is considered. Four classes of states are distinguished according to the “norm – defect” scale.
Transport and Telecommunication Journal, 2021
This paper proposes a method of automatic speaker-independent recognition of human psycho-emotion... more This paper proposes a method of automatic speaker-independent recognition of human psycho-emotional states by analyzing the speech signal based on Deep Learning technology to solve the problems of aviation profiling. For this purpose, an algorithm to classify seven human psycho-emotional states, including anger, joy, fear, surprise, disgust, sadness, and neutral state was developed. The algorithm is based on the use of Mel-frequency cepstral coefficients and Mel spectrograms as informative features of speech signals audio recordings. These informative features are used to train two deep convolutional neural networks on the generated dataset. The developed classifier testing on a delayed verification dataset showed that the metric for the multiclass fraction of correct answers’ accuracy is 0.93. The solution proposed in the paper can be in demand in human-machine interfaces creation, medicine, marketing, and in the field of air transportation.
Handbook of Pre-Clinical Continuous Intravenous Infusion, 2000
Proceedings of Computer Graphics International 2018 on - CGI 2018, 2018
The Visual Computer, 2018
Journal of Advanced Research in Law and Economics, 2019
The relevance of the study is due to the fact that not a single sovereign country agrees to allow... more The relevance of the study is due to the fact that not a single sovereign country agrees to allow uncontrolled commercial activity of foreign airlines on its territory. Hence the need for a clear international legal regulation of the rights to carry out such commercial activities. In this context, the article aims to analyze the main forms and methods of commercial activity. Leading approach to the study of this problem is the descriptive method that has afforded revealing peculiarities of terms of commercial agreements and proposed air fares. The materials of the paper imply the practical significance for the university teachers of the economic and legal specializations.