syncogest

Informations

Team

person position role skills
theo.biasutto-lervat@inria.fr SED scrum master Python, speech processing, vac
louis.abel@loria.fr Multispeech product owner Python, 3Drendering, speech processing
hugo.bergerat@loria.fr Multispeech developer Js/Ts, web dev, 3Drendering
bertrand.wallrich@inria.fr SED developer Js/Ts, web dev
laurent.pierron@inria.fr SED developer Python, Web dev

SYNCOGEST Overview

The SYNCOGEST project aims at modeling a part of the gestuality (mimics, postures and gestures) spontaneously deployed by speakers and their interlocutors during face-to-face communication, with a view to endowing embodied virtual conversational agents (ECAs) with a more natural and efficient attitude in interactional context. The aim is to propose a model for the automatic generation of appropriate gestures synchronized with speech in production (communicative gestures). This project is based on the articulation of complementary interdisciplinary approaches, bringing together specialists in artificial intelligence, language sciences and movement sciences.

Sprint Goals

The sprint aims to provide a web-based ECA relying on the vac framework developed at multispeech.

To do so, we will work on these subgoals:

  • create a vac pipeline to handle the ECA core logic,
  • update vac server with new features (remote procedure call, pipeline information given to the client and so on),
  • defining a javascript library to ease the connection to a vac server,
  • prototyping a web site using Three.js for the agent rendering.