Séminaire Thibault Roux

Seminar from Thibault Roux, PhD student at LS2N, cosupervised by LIA and LIUM   Date: 20/01/2023 Time: 10h00 Localization: IC2, Boardroom and on line Speaker: Thibault Roux     Evaluation of Language Model Rescoring in Automatic Speech Recognition   Evaluating automatic speech recognition (ASR) systems is a classical but difficult and still open problem, which […]

Séminaire Mano Brabant

Seminare from Mano Brabant, PhD student at LIUM   Date: 6/01/2023 Time: 11h00 Localization: IC2, Boardroom Speaker: Mano Brabant     Lightning exploration in interpretability of speech systems. XAI (eXplainable Artificial Inteligence) is a research field that focuses on the understanding and explanation of Machine Learning systems. Recent Deep Learning systems are more and more […]

Séminaire Rémi Uro

Seminar from Rémi Uro, PhD student at INA   Date: 9/12/2022 Time: 11h00 Localization: IC2 auditorium, and online Speakers: Rémi Uro     Anticipation of end of speech turn for interruption detection   The Gender Equality Monitor project, coordinated by INA, aims to develop automatic methods to analyze the representation of women and men in […]

Séminaire Salima Mdhaffar

Seminar from Salima Mdhaffar, postdoc at LIA, Avignon University   Date: 25/11/2022 Time: 11h00 Localization: IC2 auditorium, and online Speakers: Salima Mdhaffar     End-to-end model for named entity recognition from speech without paired training data   Recent works showed that end-to-end neural approaches tend to become very popular for spoken language understanding (SLU). Through […]

Séminaire sur la Méthode de pré-enregistrement d’expérimentations

Presentation on the preregistration method for scientific experimentations Date : 29/11/2022 Time : 15h30 Location : Zoom (ID : 829 1907 9458, code : 568689) Speaker : Estefanya Charlotte Vazquez Casaubon, PhD student from Ghent University   Abstract : Preregistration is the practice of registering the hypotheses, methods, and/or analyses of a scientific study before […]

Séminaire Julien Hauret

Seminar from Julien Hauret, PhD students at LMSSC (CNAM de Paris)   Date: 10/11/2022 Time: 11h00 Localization: IC2 auditorium, and online Speakers: Julien Hauret     Extension of the bandwidth for voice signals captured by noise-proof microphones   Speech recording is traditionally performed using microphones located near the speaker’s lips. However, this sound capture is […]

Présentation de CodeLab

Presentation de CodeLab Date : 18/10/2022 Time : 9h30 Location : Salle de réunion au Cerium (Laval) et sur Zoom Intervenant : Jérome LEHUEN, Maitre de conférence au LIUM, équipe LST   Plan de la présentation : Contexte / motivations Caractéristiques de CodeLab Utilisation « basique » en mode console Exemples de quelques « modules […]

Séminaires Valentin Pelloin et Martin Lebourdais

Seminar from Valentin Pelloin and Martin Lebourdais, PhD students at LIUM   Date: 14/10/2022 Time: 11h00 Localization: IC2 Boardroom, Speakers: Valentin Pelloin et Martin Lebourdais       ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks Valentin Pelloin We aim at improving spoken language modeling (LM) using very large amount of automatically transcribed […]

Apprentissage de représentations pour l’enseignement de la programmation

Apprentissage de représentations pour l’enseignement de la programmation Date: 13/07/2022 Heure: 14h Lieu: Salle de réunion CERIUM Laval et Zoom (ID de réunion : 813 1843 7275 – Code secret : 971343) Intervenant: Guillaume Cleuziou, Professeur des Universités, Université d’Orléans Résumé : L’utilisation de plates-formes de validation de programmes est de plus en plus fréquente […]

Evaluation of weakly-supervised methods for aspect extraction

Seminar from Mohamed Ettaleb, Post-doctoral fellow at LIUM   Date: 01/07/2022 Time: 10h30 Localization: IC2 Boardroom, online Speaker: Mohamed Ettaleb   Evaluation of weakly-supervised methods for aspect extraction     Aspect-based sentiment analysis (ABSA) may provide more detailed information than general sentiment analysis. It aims to extract aspects from reviews and predict their polarities. In […]