Chloé Clavel

Senior Researcher (Directrice de recherche) INRIA Paris

Projects

Ongoing projects:

2023-2026: National French Project (ANR) SINNet : socio-inspired neural networks for conversational systems 

Abstract: SINNet proposes a paradigm shift for rendering conversational systems and social robotics a more acceptable and trustworthy technology even when using deep learning approaches. It will focus on the verbal component of the interaction, will target the agent-user social relationship, and model the behaviors indexing the state of the social relationship between agent and user, going thus beyond the analysis of the user’s positive and negative sentiments. It implies developing easy-to-adapt and easy-to-explain neural models able to analyze the user’s behavior contributing to user- agent co-construction processes such as the ones characterizing the rapport with the agent, or the trust and affiliation in the agent, as well as to generate the agent’s answer fostering the user-agent social relationship. This SINNet project will establish interdisciplinarity as a core challenge by providing a shared formalism between complex (e.g., psychological or socio- linguistic) theories of social interactions and the underlying formalism in deep learning and language models.

2022- 2025 : National French Project (ANR) – REVITALISE – viRtual bEhaVioral skIlls TrAining for pubLIc SpEaking
Abstract: More than ever, with the increasing use of online video-conferencing solutions in daily professional interactions, public speaking skills are becoming crucial. The aim of this project is to obtain better insights into the best approaches allowing the practice of public speaking skills with technologically mediated tools. To this end, we will investigate different training environments (ex: w/o a virtual/real audience) and different training approaches (e.g., modeling-based, feedback-based, simulation-based) to help users acquire, improve, and practice public speaking skills in full autonomy. For this purpose, different research challenges will be tackled to 1/ automatically learn, from different corpora, the multimodal cues correlated to the quality of public speaking; 2/ provide pedagogical activities rooted in coaching practice, taking a user-centered approach and 3/ provide a global evaluation of the training session as well as the specific behavioral characteristics to improve.

H2020 ITN ANIMATAS – Advancing intuitive human-machine interaction with human-like social capabilities for education in schools

2018-2023 DSAIDIS chair (Data science & artificial intelligence For digitalized industry & services) is a Télécom ParisTech Chair . Established for a five-year period with the help of the Fondation Mines-Télécom and the support of Airbus Defence & Space, Engie, Idemia, Safran and Valeo, it aims at developing methodological research addressing the industrial challenges posed by the machine learning and artificial intelligence.

2019-2024 NORdf chair  – Selected and financially supported by the French National Research Agency (ANR)

Past projects:

AI4Softskills – Artificial Intelligence for Training Soft Skills :   Carnot Institute funding 

ANR JCJC MAOI – Multimodal Analysis of Opinions in Interactions – Principal Investigator

The Chair Machine Learning for Big data is a Télécom ParisTech Chair. It aims at developing methodological research addressing the challenges posed by the statistical analysis of big data.

The French national ANR project ACORFORMed (2015-2017) : Virtual Reality for Training Doctors to Break Bad News.

The ARIA-VALUSPA  EU ICT project (2015­2018) (Affective Retrieval Interface Assistants  –  using Virtual Agents with Linguistic Understanding, Social skills and Personalised Aspects). The project tackles the development of ECA whose function is to serve as interface for retrieval systems and to provide a more natural answer to user’s requests.

Sense project in the context of Smart labex : the project focuses on socio-emotional signals in interactions and deals with research issues covering the signal capture (audio, video, neurophysiologic), the socio-emotional  signal interpretation and modelisation and its exploitation (virtual agents, musical interaction, group of persons).  The model developed through the project will be evaluated through realistic scenarios.

French national project A1:1: dialog with a life-size avatar in a cultural place, including verbal and non verbal communication dimensions.

French national project ANR ImagiWeb

The Equipex (Equiment of Excellence) DIME-SHS (Données Infrastructures et Méthodes d’Enquête en Sciences Humaines et Sociales) : member of scientific committee

French national project Voxfactory: emotion recognition and sentiment analysis in call-centres

French national project Doxa: design a solution for automatically understanding and interpreting subjective data such as opinions and sentiments

ITEA european project SERKET