Phonetic encoding method in the isolated words recognition problem

Theory and Methods of Signal Processing

DOI: 10.1134/S1064226914040093

Cite this article as:
Savchenko, A.V. J. Commun. Technol. Electron. (2014) 59: 310. doi:10.1134/S1064226914040093

Abstract

A phonetic approach to the problem of automatic recognition of isolated words is investigated. The phonetic encoding method whereby each word from a vocabulary is associated with the code sequence of stable phonemes is proposed. The information-theoretical estimate of vocabulary confusability, the calculations of which rely on the phonetic database of a speaker and the communications channel SNR, is synthesized using the Kullback-Leibler divergence properties. In the experimental study of the proposed method, the mutual influence between the recognition quality and the proposed estimate of confusability is demonstrated by solving the problem of recognition of words in the Russian speech. It is established that the introduced requirement to isolated syllable pronunciation makes it possible to attain the 90–95% accuracy of recognition for vocabularies containing 2000 words.

Copyright information

© Pleiades Publishing, Inc. 2014

Authors and Affiliations

  1. 1.National Research University Higher School of EconomicsNizhni NovgorodRussia

Personalised recommendations