Supervision distante d’un système de transcription automatique de la parole Encadrant(s): Antoine Laurent Equipe d’accueil : LIUM – LST Lieu : Le Mans Contexte : Le stage s’inscrit dans le thème de la reconnaissance automatique de la parole. Il vise à contribuer au développement de systèmes entièrement neuronaux pour l’apprentissage de représentations de manière […]
Biométrie Vocale : du signal audio à l’identité de la personne Encadrant(s): Anthony Larcher Equipe d’accueil : LIUM – LST Lieu : Le Mans Contexte : Un étudiant du parcours ATAL sera plus à même de réaliser ce stage sans toutefois exclure les étudiants du parcours AFD. Contact : Anthony.Larcher(at)univ-lemans.fr, Sujet : […]
Une approche graphe/réseaux complexes pour modéliser le sens des mots Encadrant(s): Nicolas Dugué Equipe d’accueil : LIUM – LST Lieu : Le Mans Contexte :Le projet #neo s’intéresse à la détection automatique de néologismes en exploitant de grands corpus textuels. En particulier, il s’agit de détecter des mots qui changent de sens ou dont […]
SpeechBrain (SpeechBrain)Date: 09/2019 – 12/2021Funding: AutresCall: Partners: Mila (Canada), LIA (France), PyTorch, IBM Research AI, fluent.ai (Canada)URL: https://speechbrain.github.ioLIUM Participant(s): Anthony LarcherSylvain MeignierSpeechBrain is an open-source and all-in-one speech toolkit relying on PyTorch. The goal is to create a single, flexible, and user-friendly toolkit that can be used to easily develop state-of-the-art speech technologies, including systems […]
Gender Equality Monitor (GEM)Date: 01/2020 – 06/2024Funding: ANRCall: AAPG2019Partners: INA, LIMSI, Carism, Deezer, LERASS, ENS Lyon URL: https://lium.univ-lemans.fr/en/gem/LIUM Participant(s): Antoine LaurentAnthony LarcherNathalie CamelinNicolas DuguéSylvain MeignierMarie TahonMartin LebourdaisMedia and society have an intricate relationship. Descriptive, the media are also prescriptive and shape our perception of the world. The GEM project aims to describe the differences in […]
CapDiff (CapDiff)Date: 06/2019 – 12/2020Funding: AutresCall: BPIPartners: LAUM (France), HAAPIE (France), VOXPASS (France)URL: https://lium.univ-lemans.fr/en/capdiff/LIUM Participant(s): Anthony LarcherJustine CarpentierSylvain MeignierThe development and spreading of connected enable automation of a number of tidious tasks. The recent advances in speech recognition technologies, i.e., speech synthesis or voice recognition and the increasing user acceptance open wide horizons for those […]
Artificial Intelligence for Semantically controlled SPEech UndeRstanding (AISSPER)Date: 01/2020 – 10/2024Funding: ANRCall: AAPG2019Partners: LIA (France), Orkis (France)URL: https://lium.univ-lemans.fr/en/aissper/LIUM Participant(s): Nathalie CamelinSylvain MeignierAntoine LaurentValentin PelloinEffective modeling of variabilities, exhibited by human’s speech at different levels (prosodic, acoustic, lexical,…), is still an open research problem for SLU systems. Even more, extracting relevant keywords, themes or concept mentions […]
Privacy preserving and personalized transformations for speech recognitionStarting: 01/10/2019PhD Student: Pierre ChampionAdvisor(s): Denis Jouvet (Loria), Anthony Larcher (LIUM – LST)Co-advisor(s): Funding: ANR Deep-PrivacyThe objective of the proposed thesis is twofold. First, it aims at finding a privacy preserving transform of the speech data, and, second, it will investigate the use of additional personalized transforms, that […]
Analysis and countermeasures of identity theft fraud in behavioural biometric systemsStarting: 01/10/2019PhD Student: Thomas ThebaudAdvisor(s): Anthony Larcher (LIUM – LST)Co-advisor(s): Gaël Le Lan (Orange)Funding: Orange Labs
End-To-end Evolutive Neural Networks for Speaker Recognition (EXTENSOR)Date: 01/2020 – 06/2022Funding: ANRCall: AAPG2019Partners: Eurecom (France)URL: https://lium.univ-lemans.fr/en/extensor/LIUM Participant(s): Anthony LarcherAntoine LaurentMarie TahonSylvain MeignierAmbuj Mehrish ExTENSoR proposes fundamental research that aims to explore the potential of using end-to-end and automatically learned / evolving articial neural networks in order to overcome the limitations of hand-crafted features and network […]
Français