@inproceedings{fernandez-martinez-etal-2010-hifi,
title = "{HIFI}-{AV}: An Audio-visual Corpus for Spoken Language Human-Machine Dialogue Research in {S}panish",
author = "Fern{\'a}ndez-Mart{\'\i}nez, Fernando and
Lucas-Cuesta, Juan Manuel and
Chicote, Roberto Barra and
Ferreiros, Javier and
Mac{\'\i}as-Guarasa, Javier",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/230_Paper.pdf",
abstract = "In this paper, we describe a new multi-purpose audio-visual database on the context of speech interfaces for controlling household electronic devices. The database comprises speech and video recordings of 19 speakers interacting with a HIFI audio box by means of a spoken dialogue system. Dialogue management is based on Bayesian Networks and the system is provided with contextual information handling strategies. Each speaker was requested to fulfil different sets of specific goals following predefined scenarios, according to both different complexity levels and degrees of freedom or initiative allowed to the user. Due to a careful design and its size, the recorded database allows comprehensive studies on speech recognition, speech understanding, dialogue modeling and management, microphone array based speech processing, and both speech and video-based acoustic source localisation. The database has been labelled for quality and efficiency studies on dialogue performance. The whole database has been validated through both objective and subjective tests.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fernandez-martinez-etal-2010-hifi">
<titleInfo>
<title>HIFI-AV: An Audio-visual Corpus for Spoken Language Human-Machine Dialogue Research in Spanish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Fernández-Martínez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="given">Manuel</namePart>
<namePart type="family">Lucas-Cuesta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="given">Barra</namePart>
<namePart type="family">Chicote</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">Ferreiros</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">Macías-Guarasa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe a new multi-purpose audio-visual database on the context of speech interfaces for controlling household electronic devices. The database comprises speech and video recordings of 19 speakers interacting with a HIFI audio box by means of a spoken dialogue system. Dialogue management is based on Bayesian Networks and the system is provided with contextual information handling strategies. Each speaker was requested to fulfil different sets of specific goals following predefined scenarios, according to both different complexity levels and degrees of freedom or initiative allowed to the user. Due to a careful design and its size, the recorded database allows comprehensive studies on speech recognition, speech understanding, dialogue modeling and management, microphone array based speech processing, and both speech and video-based acoustic source localisation. The database has been labelled for quality and efficiency studies on dialogue performance. The whole database has been validated through both objective and subjective tests.</abstract>
<identifier type="citekey">fernandez-martinez-etal-2010-hifi</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/230_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HIFI-AV: An Audio-visual Corpus for Spoken Language Human-Machine Dialogue Research in Spanish
%A Fernández-Martínez, Fernando
%A Lucas-Cuesta, Juan Manuel
%A Chicote, Roberto Barra
%A Ferreiros, Javier
%A Macías-Guarasa, Javier
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F fernandez-martinez-etal-2010-hifi
%X In this paper, we describe a new multi-purpose audio-visual database on the context of speech interfaces for controlling household electronic devices. The database comprises speech and video recordings of 19 speakers interacting with a HIFI audio box by means of a spoken dialogue system. Dialogue management is based on Bayesian Networks and the system is provided with contextual information handling strategies. Each speaker was requested to fulfil different sets of specific goals following predefined scenarios, according to both different complexity levels and degrees of freedom or initiative allowed to the user. Due to a careful design and its size, the recorded database allows comprehensive studies on speech recognition, speech understanding, dialogue modeling and management, microphone array based speech processing, and both speech and video-based acoustic source localisation. The database has been labelled for quality and efficiency studies on dialogue performance. The whole database has been validated through both objective and subjective tests.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/230_Paper.pdf
Markdown (Informal)
[HIFI-AV: An Audio-visual Corpus for Spoken Language Human-Machine Dialogue Research in Spanish](http://www.lrec-conf.org/proceedings/lrec2010/pdf/230_Paper.pdf) (Fernández-Martínez et al., LREC 2010)
ACL