Methods for Rapid Development of Automatic Speech Recognition System for Russian

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24220%2F15%3A00002968" target="_blank" >RIV/46747885:24220/15:00002968 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ECMSM.2015.7208686" target="_blank" >http://dx.doi.org/10.1109/ECMSM.2015.7208686</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ECMSM.2015.7208686" target="_blank" >10.1109/ECMSM.2015.7208686</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Methods for Rapid Development of Automatic Speech Recognition System for Russian

Popis výsledku v původním jazyce

In this paper we present our approach to the rapid and efficient development of an automatic speech recognition (ASR) system for Russian. We try to utilize our tools, procedures and data previously designed and collected for other Slavic languages, Czech and Slovak. We show how we build a large corpus of texts acquired from major publishers' web pages and convert it from Cyrillic to Latin to simplify further processing. The corpus is used to create a representative lexicon with 218K words and 259K pronunciations and a probabilistic language model. When training the acoustic model (AM), we use the GlobalPhone database of recordings and a largely automated scheme that includes bootstrapping with an existing Czech AM and several iterative steps to gradually improve both phonetic annotations and the target Russian AM. The recent prototype of the Russian ASR system is evaluated on the test part of the GlobalPhone database and achieves 18.2 % word error rate..

Název v anglickém jazyce

Methods for Rapid Development of Automatic Speech Recognition System for Russian

Popis výsledku anglicky

In this paper we present our approach to the rapid and efficient development of an automatic speech recognition (ASR) system for Russian. We try to utilize our tools, procedures and data previously designed and collected for other Slavic languages, Czech and Slovak. We show how we build a large corpus of texts acquired from major publishers' web pages and convert it from Cyrillic to Latin to simplify further processing. The corpus is used to create a representative lexicon with 218K words and 259K pronunciations and a probabilistic language model. When training the acoustic model (AM), we use the GlobalPhone database of recordings and a largely automated scheme that includes bootstrapping with an existing Czech AM and several iterative steps to gradually improve both phonetic annotations and the target Russian AM. The recent prototype of the Russian ASR system is evaluated on the test part of the GlobalPhone database and achieves 18.2 % word error rate..

Druh

D - Stať ve sborníku

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

<a href="/cs/project/TA04010199" target="_blank" >TA04010199: MULTILINMEDIA - Multilinguální platforma pro monitoring a analýzu multimédií</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2015

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2015 IEEE International Workshop of Electronics, Control, Measurement, Signals and their application to Mechatronics

ISBN

978-1-4799-6972-2

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

26-31

Název nakladatele

IEEE

Místo vydání

Česká Republika

Místo konání akce

Česká Republika, Liberec

Datum konání akce

—

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000363814500011