@inproceedings{hofbauer-etal-2008-atcosim,
title = "The {ATCOSIM} Corpus of Non-Prompted Clean Air Traffic Control Speech",
author = "Hofbauer, Konrad and
Petrik, Stefan and
Hering, Horst",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/545_paper.pdf",
abstract = "Air traffic control (ATC) is based on voice communication between pilots and controllers and uses a highly task and domain specific language. Due to this very reason, spoken language technologies for ATC require domain-specific corpora, of which only few exist to this day. The ATCOSIM Air Traffic Control Simulation Speech corpus is a speech database of non-prompted and clean ATC operator speech. It consists of ten hours of speech data, which were recorded in typical ATC control room conditions during ATC real-time simulations. The database includes orthographic transcriptions and additional information on speakers and recording sessions. The ATCOSIM corpus is publicly available and provided online free of charge. In this paper, we first give an overview of ATC related corpora and their shortcomings. We then show the difficulties in obtaining operational ATC speech recordings and propose the use of existing ATC real-time simulations. We describe the recording, transcription, production and validation process of the ATCOSIM corpus, and outline an application example for automatic speech recognition in the ATC domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hofbauer-etal-2008-atcosim">
<titleInfo>
<title>The ATCOSIM Corpus of Non-Prompted Clean Air Traffic Control Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Konrad</namePart>
<namePart type="family">Hofbauer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Petrik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horst</namePart>
<namePart type="family">Hering</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Air traffic control (ATC) is based on voice communication between pilots and controllers and uses a highly task and domain specific language. Due to this very reason, spoken language technologies for ATC require domain-specific corpora, of which only few exist to this day. The ATCOSIM Air Traffic Control Simulation Speech corpus is a speech database of non-prompted and clean ATC operator speech. It consists of ten hours of speech data, which were recorded in typical ATC control room conditions during ATC real-time simulations. The database includes orthographic transcriptions and additional information on speakers and recording sessions. The ATCOSIM corpus is publicly available and provided online free of charge. In this paper, we first give an overview of ATC related corpora and their shortcomings. We then show the difficulties in obtaining operational ATC speech recordings and propose the use of existing ATC real-time simulations. We describe the recording, transcription, production and validation process of the ATCOSIM corpus, and outline an application example for automatic speech recognition in the ATC domain.</abstract>
<identifier type="citekey">hofbauer-etal-2008-atcosim</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/545_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The ATCOSIM Corpus of Non-Prompted Clean Air Traffic Control Speech
%A Hofbauer, Konrad
%A Petrik, Stefan
%A Hering, Horst
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F hofbauer-etal-2008-atcosim
%X Air traffic control (ATC) is based on voice communication between pilots and controllers and uses a highly task and domain specific language. Due to this very reason, spoken language technologies for ATC require domain-specific corpora, of which only few exist to this day. The ATCOSIM Air Traffic Control Simulation Speech corpus is a speech database of non-prompted and clean ATC operator speech. It consists of ten hours of speech data, which were recorded in typical ATC control room conditions during ATC real-time simulations. The database includes orthographic transcriptions and additional information on speakers and recording sessions. The ATCOSIM corpus is publicly available and provided online free of charge. In this paper, we first give an overview of ATC related corpora and their shortcomings. We then show the difficulties in obtaining operational ATC speech recordings and propose the use of existing ATC real-time simulations. We describe the recording, transcription, production and validation process of the ATCOSIM corpus, and outline an application example for automatic speech recognition in the ATC domain.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/545_paper.pdf
Markdown (Informal)
[The ATCOSIM Corpus of Non-Prompted Clean Air Traffic Control Speech](http://www.lrec-conf.org/proceedings/lrec2008/pdf/545_paper.pdf) (Hofbauer et al., LREC 2008)
ACL