@inproceedings{schmitt-etal-2012-parameterized,
title = "A Parameterized and Annotated Spoken Dialog Corpus of the {CMU} Let{'}s Go Bus Information System",
author = "Schmitt, Alexander and
Ultes, Stefan and
Minker, Wolfgang",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/333_Paper.pdf",
pages = "3369--3373",
abstract = "Standardized corpora are the foundation for spoken language research. In this work, we introduce an annotated and standardized corpus in the Spoken Dialog Systems (SDS) domain. Data from the Let's Go Bus Information System from the Carnegie Mellon University in Pittsburgh has been formatted, parameterized and annotated with quality, emotion, and task success labels containing 347 dialogs with 9,083 system-user exchanges. A total of 46 parameters have been derived automatically and semi-automatically from Automatic Speech Recognition (ASR), Spoken Language Understanding (SLU) and Dialog Manager (DM) properties. To each spoken user utterance an emotion label from the set garbage, non-angry, slightly angry, very angry has been assigned. In addition, a manual annotation of Interaction Quality (IQ) on the exchange level has been performed with three raters achieving a Kappa value of 0.54. The IQ score expresses the quality of the interaction up to each system-user exchange on a score from 1-5. The presented corpus is intended as a standardized basis for classification and evaluation tasks regarding task success prediction, dialog quality estimation or emotion recognition to foster comparability between different approaches on these fields.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schmitt-etal-2012-parameterized">
<titleInfo>
<title>A Parameterized and Annotated Spoken Dialog Corpus of the CMU Let’s Go Bus Information System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Schmitt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wolfgang</namePart>
<namePart type="family">Minker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Standardized corpora are the foundation for spoken language research. In this work, we introduce an annotated and standardized corpus in the Spoken Dialog Systems (SDS) domain. Data from the Let’s Go Bus Information System from the Carnegie Mellon University in Pittsburgh has been formatted, parameterized and annotated with quality, emotion, and task success labels containing 347 dialogs with 9,083 system-user exchanges. A total of 46 parameters have been derived automatically and semi-automatically from Automatic Speech Recognition (ASR), Spoken Language Understanding (SLU) and Dialog Manager (DM) properties. To each spoken user utterance an emotion label from the set garbage, non-angry, slightly angry, very angry has been assigned. In addition, a manual annotation of Interaction Quality (IQ) on the exchange level has been performed with three raters achieving a Kappa value of 0.54. The IQ score expresses the quality of the interaction up to each system-user exchange on a score from 1-5. The presented corpus is intended as a standardized basis for classification and evaluation tasks regarding task success prediction, dialog quality estimation or emotion recognition to foster comparability between different approaches on these fields.</abstract>
<identifier type="citekey">schmitt-etal-2012-parameterized</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/333_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3369</start>
<end>3373</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Parameterized and Annotated Spoken Dialog Corpus of the CMU Let’s Go Bus Information System
%A Schmitt, Alexander
%A Ultes, Stefan
%A Minker, Wolfgang
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F schmitt-etal-2012-parameterized
%X Standardized corpora are the foundation for spoken language research. In this work, we introduce an annotated and standardized corpus in the Spoken Dialog Systems (SDS) domain. Data from the Let’s Go Bus Information System from the Carnegie Mellon University in Pittsburgh has been formatted, parameterized and annotated with quality, emotion, and task success labels containing 347 dialogs with 9,083 system-user exchanges. A total of 46 parameters have been derived automatically and semi-automatically from Automatic Speech Recognition (ASR), Spoken Language Understanding (SLU) and Dialog Manager (DM) properties. To each spoken user utterance an emotion label from the set garbage, non-angry, slightly angry, very angry has been assigned. In addition, a manual annotation of Interaction Quality (IQ) on the exchange level has been performed with three raters achieving a Kappa value of 0.54. The IQ score expresses the quality of the interaction up to each system-user exchange on a score from 1-5. The presented corpus is intended as a standardized basis for classification and evaluation tasks regarding task success prediction, dialog quality estimation or emotion recognition to foster comparability between different approaches on these fields.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/333_Paper.pdf
%P 3369-3373
Markdown (Informal)
[A Parameterized and Annotated Spoken Dialog Corpus of the CMU Let’s Go Bus Information System](http://www.lrec-conf.org/proceedings/lrec2012/pdf/333_Paper.pdf) (Schmitt et al., LREC 2012)
ACL