The Deeplomatics project aims at detecting, localizing and identifying low sound level acoustic sources generated during UAV intrusion on sensitive areas. To do that, a multimodal approach has been chosen. Acoustical sensors coupled to an AI …
In this paper, we present Extreme Bandwidth Extension Network (EBEN), a generative adversarial network (GAN) that enhances audio measured with noise-resilient microphones. This type of capture equipment suppresses ambient noise at the expense of …
Realtime Identification and geolocalization of flying drones.
Improving speech intelligibility recorded by in-the-ear transducers
Julien Hauret's PhD thesis (2021- 2024)
Hadrien Pujol's PhD thesis (2017-2020)
TimeScaleNet, a multi-resolution time domain architecture for speech and environmental sound recognition
Project leader - DGA funding 2019-2022