39197

Автор(ы): 

Автор(ов): 

6

Параметры публикации

Тип публикации: 

Статья в журнале/сборнике

Название: 

A Russian Keyword Spotting System Based on Large Vocabulary Continuous Speech Recognition and Linguistic Knowledge

Электронная публикация: 

Да

ISBN/ISSN: 

2090-0147

DOI: 

http://dx.doi.org/10.1155/2016/4062786

Наименование источника: 

  • Journal of Electrical and Computer Engineering

Обозначение и номер тома: 

Volume 2016.

Город: 

  • London

Издательство: 

  • Hindawi Publishing Corporation

Год издания: 

2016

Страницы: 

1-9 http://dx.doi.org/10.1155/2016/4062786
Аннотация
The paper describes the key concepts of a word spotting system for Russian based on large vocabulary continuous speech recognition. Key algorithms and system settings are described, including the pronunciation variation algorithm, and the experimental results on the real-life telecom data are provided. The description of system architecture and the user interface is provided. The system is based on CMU Sphinx open-source speech recognition platform and on the linguistic models and algorithms developed by Speech Drive LLC. The effective combination of baseline statistic methods, real-world training data, and the intensive use of linguistic knowledge led to a quality result applicable to industrial use.

Библиографическая ссылка: 

Фархадов М.П., Smirnov V.., Ignatov D.., Gusev M.., Rumyantseva N.., Farkhadova M.E. A Russian Keyword Spotting System Based on Large Vocabulary Continuous Speech Recognition and Linguistic Knowledge // Journal of Electrical and Computer Engineering. 2016. Volume 2016. С. 1-9 http://dx.doi.org/10.1155/2016/4062786.