Deep Learning

Deeplomatics project: Multimodal UAV detection, localisation and identification for site surveillance

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 …

EBEN: Extreme bandwidth extension network applied to speech signals captured with noise-resilient microphones

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 …

Deeplomatics - A deep-learning based multimodal approach for aerial drone detection and localization

Realtime Identification and geolocalization of flying drones.

Deep Learning enhancement of speech signals captured with in-ear transducers

Improving speech intelligibility recorded by in-the-ear transducers

Bandwidth extension of speech signals

Julien Hauret's PhD thesis (2021- 2024)

BeamLearning - Source localization using Deep Learning

Hadrien Pujol's PhD thesis (2017-2020)

Sound recognition using Deep Learning

TimeScaleNet, a multi-resolution time domain architecture for speech and environmental sound recognition

ANR ASTRID project 'Deeplomatics'

Project leader - DGA funding 2019-2022