@inproceedings{savino-etal-2008-integrating,
title = "Integrating Audio and Visual Information for Modelling Communicative Behaviours Perceived as Different",
author = "Savino, Michelina and
Scivetti, Laura and
Refice, Mario",
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/448_paper.pdf",
abstract = "In human face-to-face interaction, participants can rely on a number of audio-visual information for interpreting interlocutors communicative intentions, such information strongly contributing to the successfulness of communication. Modelling these typical human abilities represents a main objective in human communication research, including technological applications like human-machine interaction. In this pilot study we explore the possibility of using audio-visual parameters for describing/measuring the differences perceived in interlocutors communicative behaviours. Preliminary results derived from the multimodal analysis of a single subject seem to indicate that measuring the distribution of some prosodic and hand gesture events which are temporally co-occurring contribute to the accounting of such perceived differences. Moreover, as far as gesture events are concerned, it has been observed that relevant information are not simply to be found in the occurences of single gestures, but mainly in some gesture modalities (for example, single stroke vs multiple stroke gestures, one-hand vs both-hands gestures, etc?). In this paper we also introduce and describe a software package, ViSuite, we developed for multimodal processing and used for the work described in his paper.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="savino-etal-2008-integrating">
<titleInfo>
<title>Integrating Audio and Visual Information for Modelling Communicative Behaviours Perceived as Different</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michelina</namePart>
<namePart type="family">Savino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Scivetti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mario</namePart>
<namePart type="family">Refice</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>In human face-to-face interaction, participants can rely on a number of audio-visual information for interpreting interlocutors communicative intentions, such information strongly contributing to the successfulness of communication. Modelling these typical human abilities represents a main objective in human communication research, including technological applications like human-machine interaction. In this pilot study we explore the possibility of using audio-visual parameters for describing/measuring the differences perceived in interlocutors communicative behaviours. Preliminary results derived from the multimodal analysis of a single subject seem to indicate that measuring the distribution of some prosodic and hand gesture events which are temporally co-occurring contribute to the accounting of such perceived differences. Moreover, as far as gesture events are concerned, it has been observed that relevant information are not simply to be found in the occurences of single gestures, but mainly in some gesture modalities (for example, single stroke vs multiple stroke gestures, one-hand vs both-hands gestures, etc?). In this paper we also introduce and describe a software package, ViSuite, we developed for multimodal processing and used for the work described in his paper.</abstract>
<identifier type="citekey">savino-etal-2008-integrating</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/448_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Integrating Audio and Visual Information for Modelling Communicative Behaviours Perceived as Different
%A Savino, Michelina
%A Scivetti, Laura
%A Refice, Mario
%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 savino-etal-2008-integrating
%X In human face-to-face interaction, participants can rely on a number of audio-visual information for interpreting interlocutors communicative intentions, such information strongly contributing to the successfulness of communication. Modelling these typical human abilities represents a main objective in human communication research, including technological applications like human-machine interaction. In this pilot study we explore the possibility of using audio-visual parameters for describing/measuring the differences perceived in interlocutors communicative behaviours. Preliminary results derived from the multimodal analysis of a single subject seem to indicate that measuring the distribution of some prosodic and hand gesture events which are temporally co-occurring contribute to the accounting of such perceived differences. Moreover, as far as gesture events are concerned, it has been observed that relevant information are not simply to be found in the occurences of single gestures, but mainly in some gesture modalities (for example, single stroke vs multiple stroke gestures, one-hand vs both-hands gestures, etc?). In this paper we also introduce and describe a software package, ViSuite, we developed for multimodal processing and used for the work described in his paper.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/448_paper.pdf
Markdown (Informal)
[Integrating Audio and Visual Information for Modelling Communicative Behaviours Perceived as Different](http://www.lrec-conf.org/proceedings/lrec2008/pdf/448_paper.pdf) (Savino et al., LREC 2008)
ACL