REVIEW OF MODERN PROGRAMS FOR THE RECOGNITION AND SYNTHESIS OF RUSSIAN SPEECH

Authors

  • Илья Юрьевич Кижикин Penza Cossack Institute of Technology (branch) of the Moscow State University of Technology and Management named after KG Razumovsky“
  • Юрий Антонов Penza Cossack Institute of Technology, Penza, Russian Federation

Keywords:

speech synthesizer; speech signal; language model; frame; vocoder

Abstract

In this paper, the author examines such a topic as recognition and synthesis of Russian speech and also the most convenient and easy-to-use programs that perform these functions.

First, speech recognition is considered. We are talking about speech recognition devices, the very first device could only recognize the figures spoken by man and only after almost half a century devices began to appear that began to recognize words, they were intended only for people who had serious physiological problems with typing. But in modern times, speech recognition is available on almost all gadgets, from an MP3 player to a computer. Further, the recognition task itself and the detailed stages of its implementation are considered.

Then, the tasks and execution stages are also considered, but already the speech synthesis function itself.

The result of the work is a review of programs for the synthesis of Russian speech

Published

2019-04-21

How to Cite

Кижикин, И. Ю., & Антонов, Ю. (2019). REVIEW OF MODERN PROGRAMS FOR THE RECOGNITION AND SYNTHESIS OF RUSSIAN SPEECH. Innovation in Science, Education and Business, 1. Retrieved from https://fortus-science.ru/index.php/rgu1/article/view/151