Gérard BAILLY
Directeur de Recherche CNRS
Equipe Cognitive Robotics, Interactive Systems, & Speech Processing
Département Parole et Cognition
ME CONTACTER / CONTACT ME
Mail : gerard.bailly@gipsa-lab.grenoble-inp.fr

Domaine Universitaire
BP 46
38402 Saint Martin d'Hères cedex

Bureau B358
Tél.33 (0)4 76 57 47 11
Fax : 33 (0)4 76 57 47 10
PUBLICATIONS RECENTES / RECENT PUBLICATIONS
Les derniéres publications de la collection Gipsa dans HAL

Comparing cascaded LSTM architectures for generating head motion from speech in task-oriented dialogs

Duc-Canh Nguyen, Gérard Bailly, Frédéric Elisei. Comparing cascaded LSTM architectures for generating head motion from speech in task-oriented dialogs. HCI International, Jul 2018, Las Vegas, United States. Springer, pp.164-175, 〈http://2018.hci.international/〉. 〈hal-01848063〉

Demonstrating and Learning Multimodal Socio-communicative Behaviors for HRI: Building Interactive Models from Immersive Teleoperation Data

Gérard Bailly, Frédéric Elisei. Demonstrating and Learning Multimodal Socio-communicative Behaviors for HRI: Building Interactive Models from Immersive Teleoperation Data. FAIM/ISCA Workshop on Artificial Intelligence for Multimodal Human Robot Interaction, Jul 2018, Stockholm, Sweden. ISCA, FAIM/ISCA Workshop on Artificial Intelligence for Multimodal Human Robot Interaction (AI-MHRI), pp.39-43, 2018, 〈10.21437/AI-MHRI.2018-10〉. 〈hal-01835008〉

Immersive Teleoperation of the Eye Gaze of Social Robots Assessing Gaze-Contingent Control of Vergence, Yaw and Pitch of Robotic Eyes

Remi Cambuzat, Frédéric Elisei, Gérard Bailly, Olivier Simonin, Anne Spalanzani. Immersive Teleoperation of the Eye Gaze of Social Robots Assessing Gaze-Contingent Control of Vergence, Yaw and Pitch of Robotic Eyes. 50th International Symposium on Robotics (ISR 2018), Jun 2018, Munich, Germany. pp.232-239, 2018, 〈https://www.vde.com/en/events/isr〉. 〈hal-01779633〉

The significance of scope in modelling tones in Chinese

Branislav Gerazov, Gérard Bailly, Yi Xu. The significance of scope in modelling tones in Chinese. Sixth International Symposium on Tonal Aspects of Languages (TAL2018), Jun 2018, Berlin, Germany. ISCA, Proc. TAL2018, Sixth International Symposium on Tonal Aspects of Languages, pp.183-187, 〈10.21437/TAL.2018-37〉. 〈hal-01834964〉

PySFC - A System for Prosody Analysis based on the Superposition of Functional Contours Prosody Model

Branislav Gerazov, Gérard Bailly. PySFC - A System for Prosody Analysis based on the Superposition of Functional Contours Prosody Model. 9th International Conference on Speech Prosody (Speech Prosody 2018), Jun 2018, Poznan, Poland. ISCA, 9th International Conference on Speech Prosody 2018 pp.774-778, 〈10.21437/SpeechProsody.2018-157〉. 〈hal-01821214〉

Audio-visual synchronization in reading while listening to texts: Effects on visual behavior and verbal learning

Emilie Gerbier, Gérard Bailly, Marie-Line Bosse. Audio-visual synchronization in reading while listening to texts: Effects on visual behavior and verbal learning. Computer Speech and Language, Elsevier, 2018, 47 (january), pp.79-92. 〈10.1016/j.csl.2017.07.003〉. 〈hal-01575227〉

Introduction to the special issue on auditory-visual expressive speech and gesture in humans and machines

Jeesun Kim, Gérard Bailly, Chris Davis. Introduction to the special issue on auditory-visual expressive speech and gesture in humans and machines. Speech Communication, Elsevier : North-Holland, 2018, 98, pp.63-67. 〈10.1016/j.specom.2018.02.001〉. 〈hal-01821001〉

Pattern Recognition Letters Learning Off-line vs. On-line Models of Interactive Multimodal Behaviors with Recurrent Neural Networks

Duc Canh Nguyen, Gérard Bailly, Frédéric Elisei. Pattern Recognition Letters Learning Off-line vs. On-line Models of Interactive Multimodal Behaviors with Recurrent Neural Networks. Pattern Recognition Letters, Elsevier, 2017, 100, pp.29 - 36. 〈10.1016/j.patrec.2017.09.033〉. 〈hal-01609535〉

Which prosodic features contribute to the recognition of dramatic attitudes?

Adela Barbulescu, Rémi Ronfard, Gérard Bailly. Which prosodic features contribute to the recognition of dramatic attitudes?. Speech Communication, Elsevier : North-Holland, 2017, 95, pp.78-86. 〈10.1016/j.specom.2017.07.003〉. 〈hal-01643330〉

A Generative Audio-Visual Prosodic Model for Virtual Actors

Adela Barbulescu, Rémi Ronfard, Gérard Bailly. A Generative Audio-Visual Prosodic Model for Virtual Actors. IEEE Computer Graphics and Applications, Institute of Electrical and Electronics Engineers, 2017, 37 (6), pp.40-51. 〈10.1109/MCG.2017.4031070〉. 〈hal-01643334〉

ENCADREMENT DE THESES / PhD THESIS SUPERVISED

Grenoble Images Parole Signal Automatique laboratoire

UMR 5216 CNRS - Grenoble INP - Université Joseph Fourier - Université Stendhal