Michaël Aron

PhD topic

Audiovisual to Articulatory Speech Inversion: the goal of this project consists of recovering the vocal tract shape dynamics (from vocal folds to the lips) from the acoustical speech signal, supplemented by image analysis of the speaker's face. My part focuses on the construction of an articulatory database from different modalities: ultrasound (US) images and electro-magnetic (EM) sensors for the tongue tracking, and magnetic resonance images (MRI) for the vocal tract. The underlying idea is to combine these various imaging and sensor technologies which bring complementary sources of information on the articulators either on a dynamic or a static point of view, in order to build a whole 3D+t vocal tract.

Past projects

• LORIA/INRIA Nancy: Use of Inertial Sensors to Support Video Tracking. In an Augmented Reality project, we have studied the fusion of an inertial sensor with an image-based tracking algorithm for the augmentation of video sequences. Click here to see a video.
• LMU Munich, MedienInformatik, Fluidum project: Set up an instrumented room and developp some algorithm for camera/projector calibration and hand tracking methods.

2007.01.26 : Institut de Linguistique et de Phonétique Générales et Appliquées (ILPGA) - Université Sorbonne Nouvelle - Paris 3 - Coupling electromagnetic sensors and ultrasound images for tongue tracking

Journals and Book Chapters

[1] Michaël Aron, Marie-Odile Berger, Erwan Kerrien, Yves Laprie - Acquisition multimodale de données articulatoires. Chapter of Imagerie médicale pour l'étude de la parole, Alain Marchal, Alain Cavé, to be published in September 2009.

[2] Michael Aron, Gilles Simon, Marie-Odile Berger - Use of Inertial Sensors to Support Video Tracking. Computer Animation and Virtual Worlds, Vol. 18 (02-2007), pp 57-68.

International conferences

[1] Michael Aron, Marie-Odile Berger, Erwan Kerrien- Evaluation of the uncertainty of multimodal articulatory data . Ultrafest V, New Haven, USA, March 2010.

[2] Michael Aron, Asterios Toutios, Marie-Odile Berger, Erwan Kerrien, Brigitte Wrobel-Dautcourt, Yves Laprie - Registration of Multimodal Data for Estimating the Parameters of an Articulatory Model . IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP'09), Taipei, Taiwan, April 2009.

[3] Athanassios Katsamanis, Anastasios Roussos, Petros Maragos, Michael Aron, Marie-Odile Berger - Inversion from Audiovisual Speech to Articulatory Information by Exploiting Multimodal Data. International Seminar on Speech Production (ISSP'08), Strasbourg, France, December 2008.

[4] Martine Toda, Shinji Maeda, Michael Aron, Marie-Odile Berger - Modeling Subject-Specific Formant Transition Patterns in /aSa/ Sequences. International Seminar on Speech Production (ISSP'08), Strasbourg, France, December 2008.

[5] Michael Aron, Marie-Odile Berger, Erwan Kerrien - Multimodal fusion of electromagnetic, ultrasound and MRI data for building an articulatory model. International Seminar on Speech Production (ISSP'08), Strasbourg, France, December 2008.

[6] Michael Aron, Anastasios Roussos, Marie-Odile Berger, Erwan Kerrien, Petros Maragos - Multimodality acquisition of articulatory data and processing. 16th European Signal Processing Conference (Eusipco'08), Lausanne, Switzerland, August 2008.

[7] Michael Aron, Nicolas Ferveur, Erwan Kerrien, Marie-Odile Berger, Yves Laprie - Acquisition and synchronization of multimodal articulatory data. 8th Annual Conference of the International Speech Communication Association (Interspeech'07), Antwerpen, Belgium, August 2007.

[8] Michael Aron, Erwan Kerrien, Marie-Odile Berger, Yves Laprie - Coupling electromagnetic sensors and ultrasound images for tongue tracking: acquisition setup and preliminary results. International Seminar on Speech Production (ISSP'06), Ubatuba, Brazil, December 2006.

[9] Michael Aron, Gilles Simon, Marie-Odile Berger - Handling uncertain sensor data in vision-based camera tracking. IEEE and ACM International Symposium on Mixed and Augmented Reality (ISMAR'04), Arlington, USA, November 2004.

[10] Abdol-Reza Mansouri, Amar Mitiche, Michael Aron - PDE-based region tracking without motion computation by joint space-time segmentation. IEEE International Conference on Image Processing (ICIP'03), Barcelona, Spain, September 2003.

National conferences

[1] Michael Aron, Erwan Kerrien, Marie-Odile Berger, Yves Laprie - Fusion de capteurs électromagnétiques et d'échographies pour le suivi de la langue. Orasis'07, Obernai, France. June 2007.

[2] Michael Aron, Gilles Simon, Marie-Odile Berger - Utilisation d'un capteur inertiel comme aide au suivi basé vision. 15e congrès francophone sur la Reconnaissance des Formes et l'Intelligence Artificielle (RFIA'06), Tours, France, January 2006.

Demi ATER (Attaché Temporaire d'Enseignement et de Recherche) à l'I.U.T. de St-Dié des Vosges (Nancy 1). 96h eq. TD. Modules : Synthèse d'Images, Java, Java3d (licence professionnelle ISN), Algorithmique et C (SRC 1), Maths pour la synthèse d'images (Info 2), 2008-2009.

M2 IHM, Université Paul Verlaine, Metz, "Introduction à la Réalité Augmentée", 4h cours, 20h TP, Novembre - Décembre 2007.

IUT Verdun, Services et Réseaux de Communication (SRC), 2ème année "Applications et fonctions avancées sur Internet", 8h cours, 8h TD, 16h TP, 2h examen, Octobre - Novembre 2006.

L1 mécanique-électronique, Université Paul Verlaine, Metz, "Algorithmique et Langage C", 10h TD, 6h TP, Février - Avril 2006.

IUT Verdun, Services et Réseaux de Communication (SRC), 2ème année "Applications et fonctions avancées sur Internet", 8h cours, 8h TD, 6h TP, 2h examen, Février - Mars 2006.

Praktikum Augmented Reality, Ludwig Maximilians Universität, Munich, Allemagne, 30h Augmented Reality, February - April 2005.