ON THE PROBLEM OF DEVELOPING A SYSTEM OF SPEECH PROCESSING IN REAL TIME

This article describes the methods of developing a system of speech recognition, speech translation into a foreign language, and speech synthesis. Objective: to examine the relevance of developing such systems, to consider the business processes in the field of international communication, to identify system requirements, to describe the methods of developing such systems and analysis of existing solutions.
This article discusses the following design methods: analysis of models of existing solutions and building a model of the future solutions on this basis, building a data flow diagram (DFD-model), building an entity-relationship diagram (ERD-model).
In describing of the problem of developing of the system have been solved several non-trivial problems, such as reading the speech, analysis, translation into a foreign language, simulation of the speaker’s voice.
For the implementation of speech analysis methods are applied, which are used in the voice cloning: Spectral analysis of the speech signal based on the fast Fourier transform, mathematical dynamic programming unit (DP-method), the algorithm of a marking of pitches of the speech signal.
Discussed in this article a system of speech processing allows to simplify the communication between different cultures.

Keywords

Problem of international communication, system of speech processing, automatic speech processing, speech recognition, speech analysis, speech translation, speech synthesis, voice cloning, speech cloning.

Issue number: 2
Year: 2017
ISBN:
UDK: 004.934
DOI:
Authors: Tarasov A. A., Kostin V. N.

About authors: Tarasov A.A., Student, e-mail: tarasov258@gmail.com, Kostin V.N., Candidate of Technical Sciences, Assistant Professor, e-mail: iitem1@yandex.ru, National University of Science and Technology «MISiS», 119049, Moscow, Russia.

REFERENCES:
1. Kazancheva A. F. Aktual’nost’ problem mezhkul’turnoy kommunikatsii v sovremennom polikul’turnom prostranstve (The urgency of the problems of intercultural communication in modern multicultural space), Pyatigorsk, PGLU, 2012, 1 p.
2. Vladenie inostrannymi yazykami. Vladenie inostrannymi yazykami. FOM, available at: http://fom.ru/Nauka-i-obrazovanie/10998 (accessed 13.11.2015).
3. Mehrabian, Albert; Ferris, Susan R. Inference of Attitudes from Nonverbal Communication in Two Channels. Journal of Consulting Psychology, 1967, 31(3), pp. 248–252. doi: 10.1037/h0024648.
4. Avtomaticheskaya segmentatsiya i markirovka rechevogo signala. BLOG Web Programmista, available at: http://juice-health.ru/archive/38-kompyuternyj-sintez-i-klonirovanie-rechi/184-avtomaticheskaya-segmentatsiya (accessed 25.03.2016).
5. BPF (Bystroe preobrazovanie Fur’e). Kontrol’no-izmeritel’nye pribory i sistemy, available at: http://www.kipis.ru/info/index.php?ELEMENT_ID=40417 (accessed 27.03.2016).
6. Spektroanalizator my na nem vidim? ProSound.iXBT.com, available at: http://prosound.ixbt.com/education/spektr-analys.shtml (accessed 27.03.2016).
7. Chastota diskretizatsii, available at: https://ru.wikipedia.org/wiki/%D0%A7%D0%B0%D1%81%D1%82%D0%BE%D1%82%D0%B0_%D0%B4%D0%B8%D1%81%D0%BA%D1%80%D0%B5%D1%82%D0%B8%D0%B7%D0%B0%D1%86%D0%B8%D0%B8 (accessed 27.03.2016).
8. Lobanov B. M., Kiselev V. V. Mezhdunarodnaya konferentsiya Dialog-2003. Sbornik nauchnykh trudov (International conference Dialog-2003. Collection of scientific papers), Moscow, pp. 417–424.
9. Okno (vesovaya funktsiya), available at: https://ru.wikipedia.org/wiki/%D0%9E%
D0%BA%D0%BD%D0%BE_(%D0%B2%D0%B5%D1%81%D0%BE%D0%B2%D0%B0%D1%8F_%D1%84%D1%83%D0%BD%D0%BA%D1%86%D0%B8%D1%8F) (accessed 03.04.2016).
Subscribe for our dispatch