Vous êtes ici : Accueil » Kiosque » Annonce

Identification

Identifiant: 
Mot de passe : 

Mot de passe oublié ?
Détails d'identification oubliés ?

Annonce

18 mai 2018

12 to 18 months Postdoctoral position on speaker identification and 3D Gesture Recognition, Caen, France


Catégorie : Post-doctorant


We are seeking an outstanding postdoctoral research fellows with experience in deep learning / machine learning to work with us at Caen University, France on two projects :

  • Design of algorithms for speaker identification for intelligent home speakers and
  • 3D Gesture Recognition for intelligent human machine interfaces


1) Design of algorithms for speaker identification for intelligent home speakers.

Context:
---------
The postdoctoral position is funded under the research project HomeKeeper supported by the French National Future Investments Program. The HomeKeeper project gathers companies and universities around the design of a personal home speaker assistant that communicates with humans through sound media. Within this framework, the personal assistant should be able to discriminate the different persons living in a house and entitled to communicate with it.

Background:
-----------
Intelligent Home Speakers such as Amazon Echo and Google Home are a causing a wave of excitement amongst consumers. Their shipments reached 5.9 million units globally in 2016 and should grow tenfold by 2022. The promise of conversational, hands-free interaction with the Internet is a very compelling one and the development of personal home speaker assistants is likely to strongly benefit of cutting-edge research developments in speech recognition, especially with the recent advent of Deep Learning techniques. Such advancements in voice biometrics and voice authentication will help ease privacy concerns and make the devices more adaptable to multi-user environments. The Home- Keeper project falls within that line of research and aims at developing an innovative intelligent home speaker connected to a service platform, and will rely on Artificial Intelligence and vocal interaction to ensure secure access to the services.

Objectives and challenges:
---------------------------
Several bottlenecks will have to be overpassed in order to perform the speaker identification. The first one will consists in defining a deep learning architecture sufficiently generic for the framework of the application. The second challenge will consists to deal with the re- duced number of available data. This problem is particularly challenging in the deep learning context which usually require huge mass of data in order to perform an accurate learning. The insight of the project will be focused on these two points, the second one being hardly addressed by the literature.

Work plan:
-----------
The position will start by a large state of the art and an encoding of the best non deep methods. This first step should take 3 months and will allow to provide a first result to the other partners of the project.
The second step, evaluated to 6 months will consists in designing a deep learning architecture and to train it in order to identify several members of the project.
The last step, evaluated to 3 month, will consists in designing a first functional prototype and to evaluate its performances (in terms of size of the training set, precision and recall) when a deep network is trained on a new set of persons. This new training will be performed either thanks to random weighs or thanks to the weighs obtained at the previous step. The network architecture will remain unchanged.

Candidate profile:
------------------
The candidate must have a recent Ph.D. (within 5 years) in Computer Science (or Applied Mathematics) in the filed of Machine Learning. Knowledge and experience within the Deep Learning frameworks is also very welcomed. The candidate will perform research and algorithmic development and solid programming skills are required. Excellent interpersonal skills and the ability to work well individually or as a member of a project team are recommended. Good written and verbal communication skills are required, the candidate has to be fluent in spoken French or English and written English. Working language can be English or French.

Location:
-----------
Caen, France in the GREYC UMR CNRS laboratory. Situated in the Normandy region of France close to the sea and about 240km west of Paris; the city still has many old quarters, a population of around 120,000; the city area has roughly 250,000 inhabitants.

Some photos: https://caen.maville.com/info/detail-galerie_-Caen-en-images-_344_GaleriePhoto.Htm


Application:
-------------
Interested candidates should submit their application to

luc.brun@ensicaen.fr and
olivier.lezoray@unicaen.fr

Please include in your application email one Curriculum Vitae, one statement of research letter ex- plaining your interest and your skills for this position, and 2 reference letters (all in a single pdf file). Applications will be admitted until the position is filled.

Additional information:
-----------------------
Host institution: University of Caen Normandy and CNRS, GREYC laboratory (UMR 6072)
Gross Salary: 2074 euros per month (charges included)
Duration: One year, expendable to 18 months
Starting date: from September 2018
Advantages: Possibility of French courses, participation in transport costs, possibility of restoration on site.

*********************************************************************

2) 3D Gesture Recognition for intelligent human machine interfaces.

We are seeking an outstanding postdoctoral research fellow with
experience in deep learning to work with us at Caen University, France
on a project investigating the design of algorithms for 3D gesture recognition.

Context:
---------

The postdoctoral position is funded under the research project IGIL
supported by the Region Normandy (France). The IGIL project gathers
companies and universities around the design of new generation
human/computer interfaces using tactile and non tactile recognition of
gestures.

The present post doc is focused on non tactile interaction by the
recognition of gestures implying both hands and arms.

Background:

3D gesture recognition is becoming more and more popular and is now
integrated in commercial solutions such as gesture control in cars
like BMW. However, gesture recognition may be applied in a much wider
set of applications where complex interactions (which can not be
easily performed by voice) occur and where a tactile contact with the
screen is not possible or not convenient. The IGIL project falls
within that line of research and aims at developing a generic and
innovative intelligent 3D gesture recognition system able to
recognized complex gestures made by both hands with an identification
of individual fingers.

Objectives and challenges:
---------------------------

The project will be based on available commercial tools to extract the
skeleton of the arms / fingers. This point is thus not an objective of
the post doc who will focus his work on the recognition step.

The first objective will thus consist in evaluating the main deep and non deep methods on a small data-set conjointly designed with the company working on this project. Evaluation on larger available datasets will be also performed but one of the objective of the project is to enable the insertion of new gestures with few examples. Based on this
evaluation the post doc will have to propose an original deep learning
architecture and evaluate/improve it. Let us note that within this
framework the size of the data sets will constitute a challenge since
deep learning usually requires huge amount of data.


Work plan:
-----------

As previously mentioned , the position will start by a large state of
the art and an encoding of the best methods. This first step
should take 3 months and will allow to provide a first result to the
other partners of the project. The second step, evaluated to 12 months
will consists in designing a deep learning architecture and to train
it in order to recognize gestures both on available datasets and on a
data set defined within the project. The last step, evaluated
to 3 month, will consists in designing a functional prototype
and to evaluate its performances (in terms of size of the training
set, precision and recall) to be distributed among the members of the project.

Candidate profile:
------------------

The candidate must have a recent Ph.D. (within 5 years) in Computer Science (or Applied Mathematics) in the filed of Machine Learning.

Knowledge and experience within the Deep Learning frameworks is also very welcomed.

The candidate will perform research and algorithmic development and
solid programming skills are required.

Interpersonal skills and the ability to work well
individually or as a member of a project team are recommended.

Good written and verbal communication skills are required, the
candidate has to be fluent in spoken French or English and written
English. Working language can be English or French.

Location:
-----------
Caen, France in the GREYC UMR CNRS laboratory. Situated in the Normandy region of France close to the sea and about 240km west of Paris; the city still has many old quarters, a population of around 120,000; the city area has roughly 250,000 inhabitants.

Some photos: https://caen.maville.com/info/detail-galerie_-Caen-en-images-_344_GaleriePhoto.Htm


Application:
-------------
Interested candidates should submit their application to

luc.brun@ensicaen.fr and
olivier.lezoray@unicaen.fr

Please include in your application email one Curriculum Vitae, one statement of research letter ex- plaining your interest and your skills for this position, and 2 reference letters (all in a single pdf file). Applications will be admitted until the position is filled.

Additional information:
-----------------------
Host institution: University of Caen Normandy and CNRS, GREYC laboratory (UMR 6072)
Gross Salary: 2500 euros per month (charges included)
Duration: 18 months with possible extensions.
Starting date: from September 2018
Advantages: Possibility of French courses, participation in transport costs, possibility of restoration on site.

 

Dans cette rubrique

(c) GdR 720 ISIS - CNRS - 2011-2018.