Results, publications, deliverables

Results, publications, deliverables

Project publications will be listed here as they are released. The consortium is committed to reaching a total of at least 25 publications in journals and peer-reviewed conferences, and all modules developed inside the project will be made available through an open-source repository by the end of the project.

Selected background publications of the consortium

  • V. Sucal, M. Jullien, A. Njifenjou, F. Lefèvre, « LLM-based agentic workflow on verbal and non-verbal audiovisual perceptions and actions for proactive situated human-robot interactions » 13th International Conference on Human-Agent Interaction (HAI), 2025.
  • X. Alameda-Pineda et al., « Socially pertinent robots in gerontological healthcare » International Journal of Social Robotics, 2025.
  • T. Dhaussy, B. Jabaian, F. Lefèvre, « FlowAct: a proactive multimodal human-robot interaction system with continuous flow of perception and modular action sub-systems » IJCAI (under review), 2024.
  • T. Parcollet et al., « LeBenchmark 2.0: a standardized, replicable and enhanced framework for self-supervised representations of French speech » Computer Speech & Language, 2024.
  • A. Njifenjou, V. Sucal, B. Jabaian, F. Lefèvre, « Role-play zero-shot prompting with Large Language Models for open-domain human-machine conversation » arXiv, 2024.
  • T. Deschamps-Berger, L. Lamel, L. Devillers, « Multiscale contextual learning for speech emotion recognition in emergency call center conversations » ICMI, 2023.
  • T. Dhaussy, B. Jabaian, F. Lefèvre, R. Horaud, « Audio-visual speaker diarization in the framework of multi-user human-robot interaction » IEEE ICASSP, 2023.
  • T. Dhaussy, B. Jabaian, F. Lefèvre, « Interaction acceptance modelling and estimation for a proactive engagement in the context of human-robot interactions » IEEE/CVF ICCV Workshops, 2023.
  • F. Lefèvre, T. Dhaussy, B. Jabaian, A. Njifenjou, V. Sucal, « muDialBot, vers l’interaction humain-robot multimodale pro-active » CORIA-TALN, 2023.
  • T. Cordier, L. M. Rojas-Barahona, T. Urvoy, F. Lefèvre, « Diluted near-optimal expert demonstrations for guiding dialogue stochastic policy optimisation » NeurIPS Workshop: Human in the Loop Dialogue Systems, 2020.

Deliverables

IDDeliverableDuePartners
D1.1Evaluation of algorithms for extracting audio and visual cuesM18INRIA
D1.2Evaluation of algorithms for continual audiovisual adaptationM30INRIA
D1.3Methods for simulation of behavior understanding modulesM36INRIA, LIA
D2.1Evaluation of algorithms for automatic speech recognition and understandingM33LIA
D2.2Methods for emotion detectionM33LISN
D2.3Evaluation of adapted algorithms in simulated environmentsM36LISN, LIA, INRIA
D3.1Development of a vocal chatbotM30LIA, LISN
D3.2A multimodal stochastic observation fusion moduleM36LIA, INRIA
D3.3Online learning of engagement strategiesM42LIA, LISN, INRIA
D3.4Evaluation of adapted algorithms in simulated environmentsM45LIA, LISN, INRIA
D4.1Report on collaborative scenarios, experiments, hardware and software specificationsM12AP-HP, all
D4.2Privacy and ethics guidelines for experimental validation and data collectionM12AP-HP, all
D4.3Report on the WoZ experiments and amended specificationsM24AP-HP, all
D4.4Data collected during WoZ experimentsM24INRIA, all
D4.5Report of each iterative evaluationM36AP-HP, all
D4.6Performance of the full architecture in complex collaborative scenariosM47AP-HP, all
D5.1AnandaBot websiteM3LIA
D5.2List of scientific publicationsM24, M36, M48LIA
D5.3Data management planM24All
D5.4Project periodic reportsM12, M24, M36, M48All
D5.5Project final reportM48All