@inproceedings{scherer-etal-2012-audiovisual,
title = "An audiovisual political speech analysis incorporating eye-tracking and perception data",
author = "Scherer, Stefan and
Layher, Georg and
Kane, John and
Neumann, Heiko and
Campbell, Nick",
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/1011_Paper.pdf",
pages = "1114--1120",
abstract = "We investigate the influence of audiovisual features on the perception of speaking style and performance of politicians, utilizing a large publicly available dataset of German parliament recordings. We conduct a human perception experiment involving eye-tracker data to evaluate human ratings as well as behavior in two separate conditions, i.e. audiovisual and video only. The ratings are evaluated on a five dimensional scale comprising measures of insecurity, monotony, expressiveness, persuasiveness, and overall performance. Further, they are statistically analyzed and put into context in a multimodal feature analysis, involving measures of prosody, voice quality and motion energy. The analysis reveals several statistically significant features, such as pause timing, voice quality measures and motion energy, that highly positively or negatively correlate with certain human ratings of speaking style. Additionally, we compare the gaze behavior of the human subjects to evaluate saliency regions in the multimodal and visual only conditions. The eye-tracking analysis reveals significant changes in the gaze behavior of the human subjects; participants reduce their focus of attention in the audiovisual condition mainly to the region of the face of the politician and scan the upper body, including hands and arms, in the video only condition.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="scherer-etal-2012-audiovisual">
<titleInfo>
<title>An audiovisual political speech analysis incorporating eye-tracking and perception data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Scherer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Layher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Kane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heiko</namePart>
<namePart type="family">Neumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nick</namePart>
<namePart type="family">Campbell</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>We investigate the influence of audiovisual features on the perception of speaking style and performance of politicians, utilizing a large publicly available dataset of German parliament recordings. We conduct a human perception experiment involving eye-tracker data to evaluate human ratings as well as behavior in two separate conditions, i.e. audiovisual and video only. The ratings are evaluated on a five dimensional scale comprising measures of insecurity, monotony, expressiveness, persuasiveness, and overall performance. Further, they are statistically analyzed and put into context in a multimodal feature analysis, involving measures of prosody, voice quality and motion energy. The analysis reveals several statistically significant features, such as pause timing, voice quality measures and motion energy, that highly positively or negatively correlate with certain human ratings of speaking style. Additionally, we compare the gaze behavior of the human subjects to evaluate saliency regions in the multimodal and visual only conditions. The eye-tracking analysis reveals significant changes in the gaze behavior of the human subjects; participants reduce their focus of attention in the audiovisual condition mainly to the region of the face of the politician and scan the upper body, including hands and arms, in the video only condition.</abstract>
<identifier type="citekey">scherer-etal-2012-audiovisual</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/1011_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1114</start>
<end>1120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An audiovisual political speech analysis incorporating eye-tracking and perception data
%A Scherer, Stefan
%A Layher, Georg
%A Kane, John
%A Neumann, Heiko
%A Campbell, Nick
%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 scherer-etal-2012-audiovisual
%X We investigate the influence of audiovisual features on the perception of speaking style and performance of politicians, utilizing a large publicly available dataset of German parliament recordings. We conduct a human perception experiment involving eye-tracker data to evaluate human ratings as well as behavior in two separate conditions, i.e. audiovisual and video only. The ratings are evaluated on a five dimensional scale comprising measures of insecurity, monotony, expressiveness, persuasiveness, and overall performance. Further, they are statistically analyzed and put into context in a multimodal feature analysis, involving measures of prosody, voice quality and motion energy. The analysis reveals several statistically significant features, such as pause timing, voice quality measures and motion energy, that highly positively or negatively correlate with certain human ratings of speaking style. Additionally, we compare the gaze behavior of the human subjects to evaluate saliency regions in the multimodal and visual only conditions. The eye-tracking analysis reveals significant changes in the gaze behavior of the human subjects; participants reduce their focus of attention in the audiovisual condition mainly to the region of the face of the politician and scan the upper body, including hands and arms, in the video only condition.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/1011_Paper.pdf
%P 1114-1120
Markdown (Informal)
[An audiovisual political speech analysis incorporating eye-tracking and perception data](http://www.lrec-conf.org/proceedings/lrec2012/pdf/1011_Paper.pdf) (Scherer et al., LREC 2012)
ACL