KALDI Recipes for the Czech Speech Recognition Under Various Conditions

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F16%3A00303456" target="_blank" >RIV/68407700:21230/16:00303456 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-45510-5_45" target="_blank" >http://dx.doi.org/10.1007/978-3-319-45510-5_45</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-45510-5_45" target="_blank" >10.1007/978-3-319-45510-5_45</a>

Jazyk výsledku

angličtina

Název v původním jazyce

KALDI Recipes for the Czech Speech Recognition Under Various Conditions

Popis výsledku v původním jazyce

The paper presents the implementation of Czech ASR system under various conditions using KALDI speech recognition toolkit in two standard state-of-the-art architectures (GMM-HMM and DNN-HMM). We present the recipes for the building of LVCSR using SpeechDat, SPEECON, CZKCC, and NCCCz corpora with the new update of feature extraction tool CtuCopy which supports currently KALDI format. All presented recipes same as CtuCopy tool are publicly available under the Apache license v2.0. Finally, an extension of KALDI toolkit which supports the running of described LVCSR recipes on MetaCentrum computing facilities (Czech National Grid Infrastructure operated by CESNET) is described. In the experimental part the baseline performance of both GMM-HMM and DNN-HMM LVCSR systems applied on given Czech corpora is presented. These results also demonstrate the behaviour of designed LVCSR under various acoustic conditions same as various speaking styles.

Název v anglickém jazyce

KALDI Recipes for the Czech Speech Recognition Under Various Conditions

Popis výsledku anglicky

The paper presents the implementation of Czech ASR system under various conditions using KALDI speech recognition toolkit in two standard state-of-the-art architectures (GMM-HMM and DNN-HMM). We present the recipes for the building of LVCSR using SpeechDat, SPEECON, CZKCC, and NCCCz corpora with the new update of feature extraction tool CtuCopy which supports currently KALDI format. All presented recipes same as CtuCopy tool are publicly available under the Apache license v2.0. Finally, an extension of KALDI toolkit which supports the running of described LVCSR recipes on MetaCentrum computing facilities (Czech National Grid Infrastructure operated by CESNET) is described. In the experimental part the baseline performance of both GMM-HMM and DNN-HMM LVCSR systems applied on given Czech corpora is presented. These results also demonstrate the behaviour of designed LVCSR under various acoustic conditions same as various speaking styles.

Druh

D - Stať ve sborníku

CEP obor

JA - Elektronika a optoelektronika, elektrotechnika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2016

Kód důvěrnosti údajů

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

Název statě ve sborníku

Text, Speech, and Dialogue. 19th International Conference, TSD 2016

ISBN

978-3-319-45510-5

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

549

Strana od-do

—

Název nakladatele

University of Heidelberg

Místo vydání

Heidelberg

Místo konání akce

Brno

Datum konání akce

12. 9. 2016

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000389707400045