Supervision

• PhD candidates
  • Angelo Ortiz Tandazo, "Modelling early vocal learning with a simulated vocal tract", co-supervised with Emmanuel Dupoux (ENS/EHESS/Meta), started on 01/09/2023, ongoing.
  • Ovsev Beliz Ozkan, "Real-time control of prosody in silent speech interfaces", co-supervised with O. Perrotin (2024, ongoing).
  • Brooke Stephenson, "Beyond words : leveraging language models for incremental and context-aware text-to-speech synthesis", co-supervised with Laurent Besacier (LIG) and Laurent Girin, defended on 26/09/2023.
  • Sanjana Sankar, "Automatic recognition and generation of French Cued Speech using deep learning", co-supervised with D. Beautemps (GIPSA-lab), defended on 10/09/2024.
  • Marc-Antoine Georges, "Self-supervised learning of the relationships between sounds, gestures and units for the control of speech production : towards an agent learning to speak", co-supervised with Jean-Luc Schwartz, Julien Diard, and Laurent Girin, defended on 31/05/2023.
  • Yanis Ouakrim, "Towards machine translation of French sign language (LSF)", co-supervised with Annelies Braffort and Michèle Gouiffès from LISN (Orsay), and Denis Beautemps (GIPSA-lab), defended on 23/05/2025.
  • Fanny Roche, "Music sound synthesis using machine learning : Towards a perceptually relevant control space", co-supervised with Laurent Girin and Maëva Garnier, defended on 29/09/2020.
  • Maël Pouget, "Incremental text-to-speech synthesis", co-supervised with Gérard Bailly (GIPSA-lab), defended on 23/06/2017.
  • Florent Bocquelet, "Toward a brain-computer interface for speech restoration", co-supervised with Blaise Yvert (Inserm/BrainTech) and Laurent Girin (GIPSA-lab/INRIA), defended on 24/04/2017.
  • Diandra Fabre, "Augmented tongue ultrasound-based visual articulatory biofeedback : developments and clinical application", co-supervised with Pierre Badin (GIPSA-lab), Mélanie Canault and Nathalie Bedoin (DDL-Lyon), defended on 16/12/2016.
• Master student (second year)
  • Jonas Michael, Prediction de la prosodie pour les interfaces de communication silencieuse, Master thesis in cognitive sciences, co-encadrement avec Olivier Perrotin (GIPSA-lab)
  • Marion Girod-Roux - Master thesis in phonetics (Univ. Parix X): "Evaluation of a visual biofeedback protocol based on ultrasound imaging for the rehabilitation of articulatory disorders of glossectomized patients" (in French) - June 2016 - June 2017).
  • Xiaoou Wang - Master thesis in phonetics (Univ. Aix-Marseille): Developement of a pronunciation training method for chinese learner based on the visualization of tongue movements via a virtual talking head (in French) (April-September 2013).
  • Mael Pouget - PFE Grenoble-INP/Phelma - Real-time implementation of GMM-based mapping for a silent speech interface.
• Speech and language pathologists
  • Mathilde Janier : "Evaluation of a visual biofeedback protocol based on ultrasound imaging for the rehabilitation of articulatory disorders of glossectomized patients: an acoustic study" (2019-2021)
  • Camille Bach et Lorene Lambourion : Visual biofeedback for speech therapy (2013-2014).
• Others
  • Gina Yang - Phelma (2014, 3 months) - Automatic extraction of tongue contours in ultrasound images using active models.
  • Remi Vincent - Phelma (2011, 3 months) - Harmonic+noise coding for HMM-based speech synthesis.
  • Nicolas Asin - Master in Statistics - Université de Besancon (2011, 3 months) - HMM-based Text-to-speech synthesis using audio-books as acoustic material.

Grenoble Images Parole Signal Automatique laboratoire

UMR 5216 CNRS - Grenoble Alpes University