Chaque mois, le laboratoire commun invite des intervenants extérieurs à prendre la parole lors de séminaires à destination de ses partenaires.

Ce mois-ci, Antoine Deleforge, Chargé de Recherche à INRIA Nancy Grand-Est, nous fera l’honneur d’une présentation intitulée :

« Hearing the Walls of a Room: When Signal Processing and Machine Learning Meet Acoustics »

Résumé [EN]

Close your eyes, clap your hands. Can you hear the shape of the room? Is the floor made of tiles or carpet? Answering such questions using only audio signals recorded by microphones is a multifaceted and open research problem, located at the narrow intersection between the fields of mathematics, acoustics and computer science. Progress on it could make the acoustic diagnosis of rooms simpler, cheaper and more accurate, or bring improvements to the fields of spatial audio synthesis, recording and processing. This presentation will explore some facets of these questions through the angles of signal processing, machine learning and optimization, covering joint works performed in the MULTISPEECH team of Inria and the UMRAE team of Cerema over the past 4 years.

Biographie [EN]

Since January 2016, I am a tenured research scientist (Chargé de recherche) with Inria. I started in the PANAMA research group (Rennes, France) before moving to my current team MULTISPEECH (Nancy, France) in April 2018. I received the engineering B.Sc. (2008) and M.Sc. (2010) degrees in computer science and mathematics from the school Ensimag (Grenoble, France), as well as the specialized M.Sc. research degree in computer graphics, vision and robotics from the Université Joseph Fourier (Grenoble, France). In November 2013, I received the Ph.D. degree in computer sciences and applied mathematics of the university of Grenoble (France), under the supervision of Radu Horaud (PhD thesis available online in English). I was then employed as a postdoctoral fellow for two years (2014-2015) at the chair of Multimedia Communications and Signal Processing of the Friedrich-Alexander-University (Erlangen, Germany) with Prof. Walter Kellerman.

In 2014, I received the French PhD thesis award in signal image and vision, jointly delivered every year by the GRETSI, the club EEA and the GdR ISIS. I also received a best conference paper award at ICIP 2015 and a best journal paper award in 2016. I co-chaired and co-organized four special sessions on various aspects of learning-based audio scene analysis and phase retrieval at the international conferences ICASSP (2016, 2018) and LVA/ICA (2017, 2018). I initiated and coordinated the IEEE Signal Processing Cup 2019. I was the main coordinator of the Journée Science et Musique 2016 and 2017 (Rennes, France), two wide-audience one-day events on the science and technologies behind music and sounds (600 visitors/day). Since January 2018, I serve as an elected member of the IEEE technical committee on Audio Acoustics and Signal Processing.


More on the speaker’s Website.