Menu principal

Post-doc, Machine Learning for multimodal generation of social stances in Embodied Conversational Agents, Paris

Telecom ParisTech [1]
Duration:  1 year
Start: January 2017Salary: according to background and experience, from 2300 € /month

****Position description**

The postdoctoral researcher will take part within a collaboration
between Telecom ParisTech and ISIR [2] on the topic of multimodal
(jointly verbal, gestural) generation of social stances in Embodied
Conversational Agents (ECA).

The role of the post-doc will consist in developing machine learning
methods (following corpus-based approach) in order to propose a
computational model for the verbal and nonverbal generation of social
stances. The work will include the following steps:

- the automatic extraction of linguistic features related to social

- the annotation and the analysis of communicative gestures

- the development of machine learning approaches capable of learning
alignment sequences between verbal and nonverbal modalities;

- the generation of the aligned sequences in the ECA platform Greta;

- the evaluation of the model by perceptive tests.

The post-doc will be hosted at image and signal processing department of
Telecom ParisTech [3].

**Candidate profile**

As a minimum requirement, the successful candidate will have:

- A PhD degree

- A track record of research and publication in one or more of the
following areas: machine learning, signal processing, affective

- Excellent programming skills (preferably in Python and Java)

- Good command of English

The ideal candidate will also (optionally) have:

- Knowledge in probabilistic graphical models

-- More about the position

- Place of work: Paris, France

- For more information about Telecom ParisTech see [1]

-- How to apply

Applications are to be sent to Chloé Clavel [7] and Catherine Pelachaud
[6] (ISIR [2])

The application should be formatted as a single pdf file and should

- A complete and detailed curriculum vitae

- A letter of motivation

- The texts of 2 main publications

- The names and addresses of two referees


agent conversationnel animé; apprentissage automatique
Institut Mines Télécom (IMT) ParisTech
75006 Paris  
Date de début souhaitée
Langues obligatoires
Type de contrat
Type de poste
Salaire indicatif
Date limite
Informations de contact