@inproceedings{hoidekr-etal-2006-benefit,
title = "Benefit of a Class-based Language Model for Real-time Closed-captioning of {TV} Ice-hockey Commentaries",
author = "Hoidekr, Jan and
Psutka, J.V. and
Pra{\v{z}}{\'a}k, Ale{\v{s}} and
Psutka, Josef",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/615_pdf.pdf",
abstract = "This article describes the real-time speech recognition system for closed-captioning of TV ice-hockey commentaries. Automatic transcription of TV commentary accompanying an ice-hockey match is usually a hard task due to the spontaneous speech of a commentator put often into a very loud background noise created by the public, music, siren, drums, whistle, etc. Data for building this system was collected from 41 matches that were played during World Championships in years 2000, 2001, and 2002 and were transmitted by the Czech TV channels. The real-time closed-captioning system is based on the class-based language model designed after careful analysis of training data and OOV words in new (till now unseen) commentaries with the goal to decrease an OOV (Out-Of-Vocabulary) rate and increase recognition accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoidekr-etal-2006-benefit">
<titleInfo>
<title>Benefit of a Class-based Language Model for Real-time Closed-captioning of TV Ice-hockey Commentaries</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Hoidekr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">J</namePart>
<namePart type="given">V</namePart>
<namePart type="family">Psutka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aleš</namePart>
<namePart type="family">Pražák</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Psutka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article describes the real-time speech recognition system for closed-captioning of TV ice-hockey commentaries. Automatic transcription of TV commentary accompanying an ice-hockey match is usually a hard task due to the spontaneous speech of a commentator put often into a very loud background noise created by the public, music, siren, drums, whistle, etc. Data for building this system was collected from 41 matches that were played during World Championships in years 2000, 2001, and 2002 and were transmitted by the Czech TV channels. The real-time closed-captioning system is based on the class-based language model designed after careful analysis of training data and OOV words in new (till now unseen) commentaries with the goal to decrease an OOV (Out-Of-Vocabulary) rate and increase recognition accuracy.</abstract>
<identifier type="citekey">hoidekr-etal-2006-benefit</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/615_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benefit of a Class-based Language Model for Real-time Closed-captioning of TV Ice-hockey Commentaries
%A Hoidekr, Jan
%A Psutka, J. V.
%A Pražák, Aleš
%A Psutka, Josef
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F hoidekr-etal-2006-benefit
%X This article describes the real-time speech recognition system for closed-captioning of TV ice-hockey commentaries. Automatic transcription of TV commentary accompanying an ice-hockey match is usually a hard task due to the spontaneous speech of a commentator put often into a very loud background noise created by the public, music, siren, drums, whistle, etc. Data for building this system was collected from 41 matches that were played during World Championships in years 2000, 2001, and 2002 and were transmitted by the Czech TV channels. The real-time closed-captioning system is based on the class-based language model designed after careful analysis of training data and OOV words in new (till now unseen) commentaries with the goal to decrease an OOV (Out-Of-Vocabulary) rate and increase recognition accuracy.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/615_pdf.pdf
Markdown (Informal)
[Benefit of a Class-based Language Model for Real-time Closed-captioning of TV Ice-hockey Commentaries](http://www.lrec-conf.org/proceedings/lrec2006/pdf/615_pdf.pdf) (Hoidekr et al., LREC 2006)
ACL