1 code implementation • 9 Nov 2023 • Mireille Fares, Catherine Pelachaud, Nicolas Obin
Our approach is the first method for generating speech driven metaphoric gestures while leveraging the potential of Image Schemas.
no code implementations • 5 Sep 2023 • Clément Le Moine Veillon, Victor Rosi, Pablo Arias Sarah, Léane Salais, Nicolas Obin
This paper introduces BWSNet, a model that can be trained from raw human judgements obtained through a Best-Worst scaling (BWS) experiment.
no code implementations • 8 Aug 2023 • Mireille Fares, Catherine Pelachaud, Nicolas Obin
Behavior expressivity style is viewed here as the qualitative properties of behaviors.
no code implementations • 22 May 2023 • Mireille Fares, Catherine Pelachaud, Nicolas Obin
In this study, we address the importance of modeling behavior style in virtual agents for personalized human-agent interaction.
no code implementations • 3 Aug 2022 • Mireille Fares, Michele Grimaldi, Catherine Pelachaud, Nicolas Obin
The third goal is to allow zero shot style transfer of speakers unseen during training without retraining the model.
1 code implementation • 9 Oct 2021 • Mireille Fares, Catherine Pelachaud, Nicolas Obin
We propose a semantically-aware speech driven model to generate expressive and natural upper-facial and head motion for Embodied Conversational Agents (ECA).
no code implementations • 26 Jul 2021 • Laurent Benaroya, Nicolas Obin, Axel Roebel
Voice conversion (VC) consists of digitally altering the voice of an individual to manipulate part of its content, primarily its identity, while maintaining the rest unchanged.
no code implementations • 15 Apr 2021 • Clément Le Moine, Nicolas Obin, Axel Roebel
Speech Emotion Recognition (SER) task has known significant improvements over the last years with the advent of Deep Neural Networks (DNNs).
no code implementations • 15 Apr 2021 • Clément Le Moine Veillon, Nicolas Obin, Axel Roebel
A single neural network is proposed, in which a first module is used to learn F0 representation over different temporal scales and a second adversarial module is used to learn the transformation from one emotion to another.
no code implementations • JEPTALNRECITAL 2020 • Mathias Quillot, Lauriane Guillou, Adrien Gresse, Rafa{\"e}l Ferro, Rapha{\"e}l R{\"o}th, Damien Malinas, Richard Dufour, Axel Roebel, Nicolas Obin, Jean-Fran{\c{c}}ois Bonastre, Emmanuel Ethis
La voix act{\'e}e repr{\'e}sente un d{\'e}fi majeur pour les futures interfaces vocales avec un potentiel d{'}application extr{\^e}mement important pour la transformation num{\'e}rique des secteurs de la culture et de la communication, comme la production ou la post-production de voix pour les s{\'e}ries ou le cin{\'e}ma.
no code implementations • 22 Oct 2019 • Rafael Ferro, Nicolas Obin, Axel Roebel
This paper tackles GAN optimization and stability issues in the context of voice conversion.
no code implementations • LREC 2014 • Anne Lacheret, Sylvain Kahane, Julie Beliao, Anne Dister, Kim Gerdes, Jean-Philippe Goldman, Nicolas Obin, Pietr, Paola rea, Atanas Tchobanov
The main objective of the Rhapsodie project (ANR Rhapsodie 07 Corp-030-01) was to define rich, explicit, and reproducible schemes for the annotation of prosody and syntax in different genres ({\^A}{\mbox{$\pm$}} spontaneous, {\^A}{\mbox{$\pm$}} planned, face-to-face interviews vs. broadcast, etc.