RUS  ENG
Full version
JOURNALS // News of the Kabardino-Balkarian Scientific Center of the Russian Academy of Sciences // Archive

News of the Kabardin-Balkar scientific center of RAS, 2016 Issue 6, Pages 18–23 (Mi izkab203)

COMPUTER SCIENCE. MATHEMATICS

Methods and algorithms for automatic speech recognition: concise review

I. A. Gurtuevaa, I. D. Taisaevb

a Institute of Computer Science and Problems of Regional Management of KBSC of the Russian Academy of Science, 360000, KBR, Nalchik, 37-a, I. Armand street
b Kabardin-Balkar State University named after H.M. Berbekov, 360004, KBR, Nalchik, 173, Chernyshevsky street

Abstract: Almost all current automatic speech recognition systems are based on the standard procedure. Its architecture is shown in the article. Most widespread methods and algorithms are described. The authors showed the necessity of fundamentally new approach to problems of speech recognition and represented its key idea.

Keywords: Fourier transform, hidden Markov models, artificial neuron nets, acoustic variability.

Received: 31.10.2016



© Steklov Math. Inst. of RAS, 2024