Article 1219

Title of the article

MODERN SPEECH RECOGNITION METHODS FOR CONSTRUCTING A VOICE-CONTROL INTERFACE
FOR SPECIAL PURPOSE SYSTEMS 

Authors

Alekseev Il'ya Vladimirovich, Postgraduate student, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: aius@pnzgu.ru
Mitrokhin Maksim Aleksandrovich, Doctor of engineering sciences, head of sub-department of computer engineering, Penza State University (40 Krasnaya street, Penza, Russia), E-mail: vt@pnzgu.ru 

Index UDK

004.934 

DOI

10.21685/2072-3059-2019-2-1 

Abstract

Background. The object of the research is modern technologies of speech recognition. The subject of the study is methods of constructing and teaching speech recognition systems. The purpose of the work is to analyze modern speech recognition technologies using the example of some systems to determine the possibility of their use in the voice interface of management of special purpose systems.
Materials and methods. Researches were conducted with the use of methods of probability theory and methods of pattern recognition.
Results. The analysis of the requirements and limitations of the operation of the management interfaces for special purpose systems is carried out. The main aspects of the implementation of speech recognition systems and some features of various technologies for determining the structural units of speech are considered.
Conclusions. The considered speech recognition technologies are potentially applicable in the management interfaces of special systems, but further research is required to evaluate their effectiveness. 

Key words

user interface, speech interface, hidden markov model, neural networks, speech recognition 

Download PDF
References

1. Khaykin S. Neyronnye seti: polnyy kurs: per. s angl. [Neural networks: translation from English]. 2nd ed., corr. Moscow: Vil'yams, 2006, 1104 p. [In Russian]
2. Tampel' I. B. Nauchno-tekhnicheskiy vestnik informatsionnykh tekhnologiy, mekhaniki i optiki [Scientific and technical bulletin of informational technologies, mechanics and optics]. 2015, vol. 15, no. 6, pp. 957–968. [In Russian]
3. Huang X., Acero A. Spoken language processing: a guide to theory, algorithm, and system development. Prentice Hall, 2001, 1008 p.
4. Bourlard H., Hermansky H., Morgan N. Speech Communication. 1996, vol. 18, no. 3, pp. 205–231. DOI 10.1016/0167-6393(96)00003-9

 

Дата создания: 16.09.2019 09:25
Дата обновления: 16.09.2019 09:38