<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<p align="center"><b><font size="4"><br>
</font></b></p>
<p align="center"><b><font size="4">Two-year Post-doctoral Position<br>
</font></b> </p>
<div style="text-align:center"><b><br>
</b></div>
<div style="text-align:center"><i><font 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">Multimodal data analysis of behavioral and
physiological signals from human-human and human-machine
interactions</span></i></p>
</font></i></div>
<div style="text-align:center"><i><font size="4"><br>
<b><font color="#ff0000">deadline for application : 30 October</font></b><br>
</font></i></div>
<div style="text-align:center">
<p class="MsoNormal"
style="margin-bottom:0cm;margin-bottom:.0001pt;text-align:center;line-height:normal"
align="center"><i><span>Laboratoire d’Informatique et des
Systèmes (LIS) et Laboratoire Parole et Langage (LPL) <span
class="m_-5618057028784884354m_-4972020353523621735m_-1669117398472683246msoDel"><del
datetime="2018-03-09T13:30"></del></span></span></i></p>
Aix-Marseille Université & CNRS</div>
<div> <br>
</div>
<font face="Arial,sans-serif"><b><u>Keywords:</u></b> conversational
speech, multimodal data analysis, neurophysiological data, machine
learning<br>
<br>
The A*MIDEX project <i>PhysSocial</i> aims at a better<span>
understanding of the specificities of social interactions by
comparing relationships between behavior and </span>neurophysiology<span>
in human</span>‐human and human‐robot discussion. The goal of
the post-doc is to<span
class="m_-5618057028784884354m_-4972020353523621735m_-1669117398472683246msoIns"><ins
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></span><br>
<br>
The Post-doc is organized around 2 main tasks: <br>
</font>
<ul>
<li><font face="Arial,sans-serif"> <span><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-kerning:auto;font-synthesis:weight
style;font-variant:normal"></span></span><i>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> </span>language
and social cognition</font><font face="Arial,sans-serif"><span></span></font></li>
<li><font face="Arial,sans-serif"><span><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-kerning:auto;font-synthesis:weight
style;font-variant:normal"></span></span><i>Machine
learning of causal relations: </i>in a second step,<i> </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>
</ul>
<font face="Arial,sans-serif">The candidate should have a Phd in
Computer Science, Applied Mathematics, Signal or Natural Language
Processing (with solid background in machine learning).<br>
<br>
<span></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> </span>• Multimodal data processing<br>
<span> </span>• Data science applied to language
data<br>
<span> </span><br>
<br>
The post-doc is fully funded during 2 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 with publications,<br>
- A description of Phd subject,<br>
- A description of the academic background and copy of academic
records and most recent diploma,<br>
- 2 recommendation letters (including one from the Phd
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"
target="_blank">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" target="_blank">magalie.ochs@lis-lab.fr</a><br>
</font><br>
</font>For any question, contact :<br>
<br>
Laurent Prévot: <a href="mailto:laurent.prevot@univ-amu.fr"
target="_blank">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"
target="_blank">magalie.ochs@lis-lab.fr</a><br>
<a href="http://www.lsis.org/ochsm/" target="_blank">http://www.lsis.org/ochsm/</a></font>
</body>
</html>