@inproceedings{kratochvil-etal-2020-large,
title = "Large Corpus of {C}zech Parliament Plenary Hearings",
author = "Kratochvil, Jon{\'a}{\v{s}} and
Pol{\'a}k, Peter and
Bojar, Ond{\v{r}}ej",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.781",
pages = "6363--6367",
abstract = "We present a large corpus of Czech parliament plenary sessions. The corpus consists of approximately 1200 hours of speech data and corresponding text transcriptions. The whole corpus has been segmented to short audio segments making it suitable for both training and evaluation of automatic speech recognition (ASR) systems. The source language of the corpus is Czech, which makes it a valuable resource for future research as only a few public datasets are available in the Czech language. We complement the data release with experiments of two baseline ASR systems trained on the presented data: the more traditional approach implemented in the Kaldi ASRtoolkit which combines hidden Markov models and deep neural networks (NN) and a modern ASR architecture implemented in Jaspertoolkit which uses deep NNs in an end-to-end fashion.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kratochvil-etal-2020-large">
<titleInfo>
<title>Large Corpus of Czech Parliament Plenary Hearings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonáš</namePart>
<namePart type="family">Kratochvil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Polák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ondřej</namePart>
<namePart type="family">Bojar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>We present a large corpus of Czech parliament plenary sessions. The corpus consists of approximately 1200 hours of speech data and corresponding text transcriptions. The whole corpus has been segmented to short audio segments making it suitable for both training and evaluation of automatic speech recognition (ASR) systems. The source language of the corpus is Czech, which makes it a valuable resource for future research as only a few public datasets are available in the Czech language. We complement the data release with experiments of two baseline ASR systems trained on the presented data: the more traditional approach implemented in the Kaldi ASRtoolkit which combines hidden Markov models and deep neural networks (NN) and a modern ASR architecture implemented in Jaspertoolkit which uses deep NNs in an end-to-end fashion.</abstract>
<identifier type="citekey">kratochvil-etal-2020-large</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.781</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6363</start>
<end>6367</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large Corpus of Czech Parliament Plenary Hearings
%A Kratochvil, Jonáš
%A Polák, Peter
%A Bojar, Ondřej
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F kratochvil-etal-2020-large
%X We present a large corpus of Czech parliament plenary sessions. The corpus consists of approximately 1200 hours of speech data and corresponding text transcriptions. The whole corpus has been segmented to short audio segments making it suitable for both training and evaluation of automatic speech recognition (ASR) systems. The source language of the corpus is Czech, which makes it a valuable resource for future research as only a few public datasets are available in the Czech language. We complement the data release with experiments of two baseline ASR systems trained on the presented data: the more traditional approach implemented in the Kaldi ASRtoolkit which combines hidden Markov models and deep neural networks (NN) and a modern ASR architecture implemented in Jaspertoolkit which uses deep NNs in an end-to-end fashion.
%U https://aclanthology.org/2020.lrec-1.781
%P 6363-6367
Markdown (Informal)
[Large Corpus of Czech Parliament Plenary Hearings](https://aclanthology.org/2020.lrec-1.781) (Kratochvil et al., LREC 2020)
ACL
- Jonáš Kratochvil, Peter Polák, and Ondřej Bojar. 2020. Large Corpus of Czech Parliament Plenary Hearings. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 6363–6367, Marseille, France. European Language Resources Association.