208 citations
- Institut Polytechnique de ParisFR44 papers
- Centre National de la Recherche ScientifiqueFR23 papers
- Services répartis, Architectures, MOdélisation, Validation, Administration des RéseauxFR14 papers
- Institut Mines-TélécomFR10 papers
- Laboratoire Traitement et Communication de l’InformationFR7 papers
- Télécom ParisFR7 papers
- Université Paris 8FR7 papers
- Université Paris-SaclayFR6 papers
- Laboratoire d'Informatique pour la Mécanique et les Sciences de l'IngénieurFR4 papers
- École Nationale Supérieure d’Informatique pour l’Industrie et l’EntrepriseFR3 papers
- Orange (France)FR3 papers
- Laboratoire d'Ingénierie Circulation TransportsFR2 papers
5 papers · 1 filter
SignSVRG: fixing SignSGD via variance reduction
Evgenii Chzhen, Sholom Schechtman
We consider the problem of unconstrained minimization of finite sums of functions. We propose a simple, yet, practical way to incorporate variance reduction techniques into SignSGD…
5Greplay: a 5G Network Traffic Fuzzer -- Application to Attack Injection
Zujany Salazar, Huu Nghia Nguyen, Wissam Mallouli +2
The fifth generation of mobile broadband is more than just an evolution to provide more mobile bandwidth, massive machine-type communications, and ultra-reliable and low-latency co…
Induced Feature Selection by Structured Pruning
Nathan Hubens, Victor Delvigne, Matei Mancas +3
The advent of sparsity inducing techniques in neural networks has been of a great help in the last few years. Indeed, those methods allowed to find lighter and faster networks, abl…
Towards Measuring and Scoring Speaker Diarization Fairness
Yannis Tevissen, Jérôme Boudy, Gérard Chollet +1
Speaker diarization, or the task of finding "who spoke and when", is now used in almost every speech processing application. Nevertheless, its fairness has not yet been evaluated b…
The Newsbridge -Telecom SudParis VoxCeleb Speaker Recognition Challenge 2022 System Description
Yannis Tevissen, Jérôme Boudy, Frédéric Petitpont
We describe the system used by our team for the VoxCeleb Speaker Recognition Challenge 2022 (VoxSRC 2022) in the speaker diarization track. Our solution was designed around a new c…