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

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 provid...

Full description

Saved in:
Bibliographic Details
Main Authors: Valentin Smirnov, Dmitry Ignatov, Michael Gusev, Mais Farkhadov, Natalia Rumyantseva, Mukhabbat Farkhadova
Format: Article
Language:English
Published: Wiley 2016-01-01
Series:Journal of Electrical and Computer Engineering
Online Access:http://dx.doi.org/10.1155/2016/4062786
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849306128898326528
author Valentin Smirnov
Dmitry Ignatov
Michael Gusev
Mais Farkhadov
Natalia Rumyantseva
Mukhabbat Farkhadova
author_facet Valentin Smirnov
Dmitry Ignatov
Michael Gusev
Mais Farkhadov
Natalia Rumyantseva
Mukhabbat Farkhadova
author_sort Valentin Smirnov
collection DOAJ
description 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.
format Article
id doaj-art-3977a23b20e843dda3bd73295e3de3d7
institution Kabale University
issn 2090-0147
2090-0155
language English
publishDate 2016-01-01
publisher Wiley
record_format Article
series Journal of Electrical and Computer Engineering
spelling doaj-art-3977a23b20e843dda3bd73295e3de3d72025-08-20T03:55:11ZengWileyJournal of Electrical and Computer Engineering2090-01472090-01552016-01-01201610.1155/2016/40627864062786A Russian Keyword Spotting System Based on Large Vocabulary Continuous Speech Recognition and Linguistic KnowledgeValentin Smirnov0Dmitry Ignatov1Michael Gusev2Mais Farkhadov3Natalia Rumyantseva4Mukhabbat Farkhadova5Speech Drive LLC, Saint Petersburg, RussiaSpeech Drive LLC, Saint Petersburg, RussiaSpeech Drive LLC, Saint Petersburg, RussiaV.A. Trapeznikov Institute of Control Sciences of RAS, Moscow, RussiaRUDN University, Moscow, RussiaRUDN University, Moscow, RussiaThe 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.http://dx.doi.org/10.1155/2016/4062786
spellingShingle Valentin Smirnov
Dmitry Ignatov
Michael Gusev
Mais Farkhadov
Natalia Rumyantseva
Mukhabbat Farkhadova
A Russian Keyword Spotting System Based on Large Vocabulary Continuous Speech Recognition and Linguistic Knowledge
Journal of Electrical and Computer Engineering
title A Russian Keyword Spotting System Based on Large Vocabulary Continuous Speech Recognition and Linguistic Knowledge
title_full A Russian Keyword Spotting System Based on Large Vocabulary Continuous Speech Recognition and Linguistic Knowledge
title_fullStr A Russian Keyword Spotting System Based on Large Vocabulary Continuous Speech Recognition and Linguistic Knowledge
title_full_unstemmed A Russian Keyword Spotting System Based on Large Vocabulary Continuous Speech Recognition and Linguistic Knowledge
title_short A Russian Keyword Spotting System Based on Large Vocabulary Continuous Speech Recognition and Linguistic Knowledge
title_sort russian keyword spotting system based on large vocabulary continuous speech recognition and linguistic knowledge
url http://dx.doi.org/10.1155/2016/4062786
work_keys_str_mv AT valentinsmirnov arussiankeywordspottingsystembasedonlargevocabularycontinuousspeechrecognitionandlinguisticknowledge
AT dmitryignatov arussiankeywordspottingsystembasedonlargevocabularycontinuousspeechrecognitionandlinguisticknowledge
AT michaelgusev arussiankeywordspottingsystembasedonlargevocabularycontinuousspeechrecognitionandlinguisticknowledge
AT maisfarkhadov arussiankeywordspottingsystembasedonlargevocabularycontinuousspeechrecognitionandlinguisticknowledge
AT nataliarumyantseva arussiankeywordspottingsystembasedonlargevocabularycontinuousspeechrecognitionandlinguisticknowledge
AT mukhabbatfarkhadova arussiankeywordspottingsystembasedonlargevocabularycontinuousspeechrecognitionandlinguisticknowledge
AT valentinsmirnov russiankeywordspottingsystembasedonlargevocabularycontinuousspeechrecognitionandlinguisticknowledge
AT dmitryignatov russiankeywordspottingsystembasedonlargevocabularycontinuousspeechrecognitionandlinguisticknowledge
AT michaelgusev russiankeywordspottingsystembasedonlargevocabularycontinuousspeechrecognitionandlinguisticknowledge
AT maisfarkhadov russiankeywordspottingsystembasedonlargevocabularycontinuousspeechrecognitionandlinguisticknowledge
AT nataliarumyantseva russiankeywordspottingsystembasedonlargevocabularycontinuousspeechrecognitionandlinguisticknowledge
AT mukhabbatfarkhadova russiankeywordspottingsystembasedonlargevocabularycontinuousspeechrecognitionandlinguisticknowledge