@inproceedings{pleva-juhar-2014-tuke,
title = "{TUKE}-{BN}ews-{SK}: {S}lovak Broadcast News Corpus Construction and Evaluation",
author = "Pleva, Mat{\'u}{\v{s}} and
Juh{\'a}r, Jozef",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/680_Paper.pdf",
pages = "1709--1713",
abstract = "This article presents an overview of the existing acoustical corpuses suitable for broadcast news automatic transcription task in the Slovak language. The TUKE-BNews-SK database created in our department was built to support the application development for automatic broadcast news processing and spontaneous speech recognition of the Slovak language. The audio corpus is composed of 479 Slovak TV broadcast news shows from public Slovak television called STV1 or Jednotka containing 265 hours of material and 186 hours of clean transcribed speech (4 hours subset extracted for testing purposes). The recordings were manually transcribed using Transcriber tool modified for Slovak annotators and automatic Slovak spell checking. The corpus design, acquisition, annotation scheme and pronunciation transcription is described together with corpus statistics and tools used. Finally the evaluation procedure using automatic speech recognition is presented on the broadcast news and parliamentary speeches test sets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pleva-juhar-2014-tuke">
<titleInfo>
<title>TUKE-BNews-SK: Slovak Broadcast News Corpus Construction and Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Matúš</namePart>
<namePart type="family">Pleva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jozef</namePart>
<namePart type="family">Juhár</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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 (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article presents an overview of the existing acoustical corpuses suitable for broadcast news automatic transcription task in the Slovak language. The TUKE-BNews-SK database created in our department was built to support the application development for automatic broadcast news processing and spontaneous speech recognition of the Slovak language. The audio corpus is composed of 479 Slovak TV broadcast news shows from public Slovak television called STV1 or Jednotka containing 265 hours of material and 186 hours of clean transcribed speech (4 hours subset extracted for testing purposes). The recordings were manually transcribed using Transcriber tool modified for Slovak annotators and automatic Slovak spell checking. The corpus design, acquisition, annotation scheme and pronunciation transcription is described together with corpus statistics and tools used. Finally the evaluation procedure using automatic speech recognition is presented on the broadcast news and parliamentary speeches test sets.</abstract>
<identifier type="citekey">pleva-juhar-2014-tuke</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/680_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1709</start>
<end>1713</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TUKE-BNews-SK: Slovak Broadcast News Corpus Construction and Evaluation
%A Pleva, Matúš
%A Juhár, Jozef
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F pleva-juhar-2014-tuke
%X This article presents an overview of the existing acoustical corpuses suitable for broadcast news automatic transcription task in the Slovak language. The TUKE-BNews-SK database created in our department was built to support the application development for automatic broadcast news processing and spontaneous speech recognition of the Slovak language. The audio corpus is composed of 479 Slovak TV broadcast news shows from public Slovak television called STV1 or Jednotka containing 265 hours of material and 186 hours of clean transcribed speech (4 hours subset extracted for testing purposes). The recordings were manually transcribed using Transcriber tool modified for Slovak annotators and automatic Slovak spell checking. The corpus design, acquisition, annotation scheme and pronunciation transcription is described together with corpus statistics and tools used. Finally the evaluation procedure using automatic speech recognition is presented on the broadcast news and parliamentary speeches test sets.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/680_Paper.pdf
%P 1709-1713
Markdown (Informal)
[TUKE-BNews-SK: Slovak Broadcast News Corpus Construction and Evaluation](http://www.lrec-conf.org/proceedings/lrec2014/pdf/680_Paper.pdf) (Pleva & Juhár, LREC 2014)
ACL