Antoine Deleforge

Antoine Deleforge is a tenured research scientist with Inria since 2016. He was a member of the PANAMA audio team (Rennes, 2016-2018), the MULTISPEECH speech team (Nancy, 2018-2023) and currently the MACARON scientific machine learning team (Strasbourg, 2023-). His research focuses on physics- and data-driven inverse and forward methods for audio and acoustics, leveraging optimization, signal processing, deep learning and generative models. In addition to about 50 scientific publications, he lead or contributed to the development of multiple open-source datasets, software and challenges around these topics.

He received the engineering B.Sc. (2008) and M.Sc. (2010) degrees in computer science and mathematics from the engineering school ENSIMAG and the Université Joseph Fourier (Grenoble) and the Ph.D. (2013) degree in computer sciences and applied mathematics of the university of Grenoble. He was then employed as a postdoctoral fellow (2014-2015) at the chair of Multimedia Communications and Signal Processing of the Friedrich-Alexander-University (Erlangen, Germany). His PhD thesis was awarded the French GRETSI-EEA-ISIS award in signal image and vision in 2014 and three of his co-authored publications received best paper awards (ICIP 2015, IJNS 2016, Forum Acusticum 2025). He co-chaired and co-organized six special sessions on various aspects of audio and acoustic signal processing at the conferences ICASSP (2016, 2018), LVA/ICA (2017, 2018) and CFA (2022, 2025). From 2018 to 2023, he served as an elected member of the IEEE technical committee on Audio Acoustics and Signal Processing (two terms). He serves as an associated editor for the EURASIP Journal on Audio, Speech, and Music Processing since 2022.