<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<div style="text-align: center;" class=""><b class=""><font class=""
size="4">PhD fellowship</font></b></div>
<div style="text-align: center;" class=""><b class=""><br class="">
</b></div>
<div style="text-align: center;" class=""><i class=""><font class=""
size="4">
<p class="MsoNormal"
style="margin-bottom:0cm;margin-bottom:.0001pt;
text-align:center;line-height:normal" align="center"><i><span
style="font-family:
"Arial","sans-serif";" lang="EN-US">Computational
model of conversational behaviors integrating behavioral
and physiological data from human-human and
human-machine interactions</span></i></p>
</font></i></div>
<div style="text-align: center;" class=""><i class=""><font class=""
size="4"><br class="">
</font></i></div>
<div style="text-align: center;" class="">
<p class="MsoNormal"
style="margin-bottom:0cm;margin-bottom:.0001pt;
text-align:center;line-height:normal" align="center"><i
style="mso-bidi-font-style:normal"><span
style="font-family:"Arial","sans-serif";mso-fareast-font-family:"Times
New Roman"; mso-fareast-language:FR">Laboratoire
d’Informatique et des Systèmes (LIS) et Laboratoire Parole
et Langage (LPL) <span class="msoDel"><del
cite="mailto:ochsm" datetime="2018-03-09T13:30"></del></span></span></i></p>
Aix-Marseille Université & CNRS</div>
<div class=""> <br>
</div>
<font face="Arial,sans-serif"><b style="mso-bidi-font-weight:normal"><u>Keywords:</u></b>
conversational speech, multimodal data analysis,
neurophysiological data, machine learning, artificial agents.<br>
<br>
The PhD project is part of an A*MIDEX project <i
style="mso-bidi-font-style:normal">PhysSocial</i> that aims at a
better<span style="mso-bidi-font-weight:bold"> understanding of
the specificities of social interactions by comparing
relationships between behavior and </span>neurophysiology<span
style="mso-bidi-font-weight:bold"> in human</span>‐human and
human‐robot discussion. The goal of the PhD is to<span
class="msoIns"><ins cite="mailto:PREVOT%20Laurent"
datetime="2018-03-03T10:08"> </ins></span>analyze the
multimodal signals (speech, eyes direction, physiological, and
neurophysiologic signals) from conversational activity using
signal processing and machine learning methodologies in order to
compare the human-human and human-robot interactions. <span
style="mso-bidi-font-weight:bold"></span><br>
<br>
The PhD is organized around 3 main tasks: <br>
</font>
<ul>
<li><font face="Arial,sans-serif"> <span style="mso-list: Ignore"><span
style="font-style: normal; font-weight: normal; font-size:
7pt; line-height: normal; font-size-adjust: none;
font-stretch: normal; font-feature-settings: normal;
font-language-override: normal; font-kerning: auto;
font-synthesis: weight style; font-variant: normal;"></span></span><i
style="mso-bidi-font-style:normal">Multimodal data
preprocessing</i>: in a first step, the objective is to
process the row data (speech, transcribed speech, eyes
tracking, physiological and neurophysiological signals)
corresponding to human-human and human-robot conversation in
order to extract time series corresponding to behavioral
features, as well as cognitive events derived from local
activity in well-defined brain areas involved in<span
style="mso-spacerun:yes"> </span>language and social
cognition</font><font face="Arial,sans-serif"><span
style="mso-list: Ignore"></span></font></li>
<li><font face="Arial,sans-serif"><span style="mso-list: Ignore"><span
style="font-style: normal; font-weight: normal; font-size:
7pt; line-height: normal; font-size-adjust: none;
font-stretch: normal; font-feature-settings: normal;
font-language-override: normal; font-kerning: auto;
font-synthesis: weight style; font-variant: normal;"></span></span><i
style="mso-bidi-font-style:normal">Machine learning of
causal relations: </i>in a second step,<i
style="mso-bidi-font-style: normal"> </i><span
style="color: black;" lang="EN-US">time series will be used
by statistical learning to identify causal relations between
behavioral and physiological features and cognitive events </span>extracted
from neurophysiological recording with fMRI. From a learning
point of view, one challenge in this project is the
high-dimensional data. We address this issue with a focus on
the features representation and selection problems.</font></li>
<li><font face="Arial,sans-serif"><span style="mso-list: Ignore"><span
style="font-style: normal; font-weight: normal; font-size:
7pt; line-height: normal; font-size-adjust: none;
font-stretch: normal; font-feature-settings: normal;
font-language-override: normal; font-kerning: auto;
font-synthesis: weight style; font-variant: normal;"></span></span><i
style="mso-bidi-font-style:normal">Computational modeling
and implementation in a humanoid robot</i>: the last step
consists in integrating the knowledge extracted from the data
sets into an existing platform (Furhat talking head) in order
to generate the appropriate behavior (speech and eyes
behavior) of the artificial agent during an interaction with
an user. The model will be evaluated through a experimentation
that will be conducted in collaboration with the other
partners of the project. </font><br>
</li>
</ul>
<font face="Arial,sans-serif">The PhD candidate should have a
master's degree completed in Computer Science, Applied
Mathematics, Signal or Natural Language Processing (with solid
background in machine learning).<br>
<br>
<span style="mso-tab-count:1"></span>The candidate should have a
strong background in machine learning and signal processing with a
focus on multimodality. Some complementary previous experience
would be appreciated in the following topics:<br>
<span style="mso-tab-count:1"> </span>• Multimodal
data processing<br>
<span style="mso-tab-count:1"> </span>• Data
science applied to language data<br>
<span style="mso-tab-count:1"> </span>• Dialogue
systems<br>
<br>
The PhD is fully funded during 3 years as part of the A*MIDEX
interdisciplinary project PhysSocial, including personalized
training, travel expenses, and conferences attendance.<br>
<br>
French language is not required.<br>
<br>
Aix Marseille University (<a href="http://www.univ-amu.fr/en"
target="_blank">http://www.univ-amu.fr/en</a>), the largest
French University, is ideally located on the Mediterranean coast,
and only 1h30 away from the Alps.<br>
</font><br>
<font face="Arial,sans-serif"><font face="Arial,sans-serif"><br>
The application files consists of the following documents: <br>
- A detailed curriculum,<br>
- A description of the academic background and copy of academic
records and most recent diploma,<br>
- A cover letter describing why the applicant wishes to
participate in this project, a justification of the
inter-disciplinary and international aspects of her/his
research, his/her training project and career Plan including
these dimensions, and his/her research’s adequacy with the
proposed topics<br>
- 2 recommendation letters (including one from the master or
equivalent diploma supervisor)<br>
<br>
</font> <br>
The application files should be sent to : </font><br>
<font face="Arial,sans-serif"><font face="Arial,sans-serif">Laurent
Prévot: <a href="mailto:laurent.prevot@univ-amu.fr">laurent.prevot@univ-amu.fr</a><br>
and </font></font><br>
<font face="Arial,sans-serif"><font face="Arial,sans-serif"><font
face="Arial,sans-serif">Magalie Ochs: <a
href="mailto:magalie.ochs@lis-lab.fr">magalie.ochs@lis-lab.fr</a><br>
<br>
<u><b>Please send your intention to apply to this PhD position
with your CV and the copy of the academic files before
July 15th</b></u><u><b></b></u><u><b><br>
</b></u><u><b> </b></u></font><u><b><br>
</b></u><u><b> </b></u></font>For any question, contact :<br>
<br>
Laurent Prévot: <a href="mailto:laurent.prevot@univ-amu.fr">laurent.prevot@univ-amu.fr</a><br>
<a href="http://www.lpl-aix.fr/person/*prevot*" target="_blank">www.lpl-aix.fr/person/*prevot*</a><br>
<br>
Magalie Ochs: <a href="mailto:magalie.ochs@lis-lab.fr">magalie.ochs@lis-lab.fr</a><br>
<a href="http://www.lsis.org/ochsm/">http://www.lsis.org/ochsm/</a></font>
</body>
</html>