The LIUM regularly invites researchers to present their work to the team.

The seminars are mainly related to IT Environments for Human Learning, speech recognition and machine translation, but the team welcomes researchers from other fields, who can lead to partnerships. These seminars are also an opportunity to discuss your work and test your prototypes with a team of passionates who will certainly give you constructive feedback.

The seminars take place either in Laval or Le Mans and are broadcast live on the other site.

Do not hesitate to contact Iza Marfisi (iza.marfisi@univ-lemans.fr) or Marie Tahon (Marie.Tahon@univ-lemans.fr) if you wish to participate!

Lightweight CNNs for Face Recognition Applications

Date: 09/10/2024
Hour: 11h00
Localisation: IC2, salle des conseils
Speaker(s): Heydi Méndez Vázquez

Heydi Méndez Vázquez, director of research at CENATAV, Cuba, who is spending 3 months at the LIUM as part of ESPERANTO, will be presenting her work on Wednesday 9 October at 11am in the boardroom. ► Read more

Séminaire de Lamia TRIQUI sur l'automatisation intelligente dans les usines

Date: 08/10/2024
Hour: 14h30
Localisation: IUT de Laval
Speaker(s): Lamia TRIQUI

Approches intelligentes pour le pilotage et la synchronisation des systèmes industriels et des chaînes logistiques ► Read more

Trustworthy, explainable, interpretable… what can we expect for speech processing?

Date: 02/07/2024
Hour: 10:OO
Localisation: IC2, salle 210
Speaker(s): Anthony Larcher

Anthony Larcher, professor at the LIUM, will be presenting his work on Tuesday 2 July at 10.00 am in the boardroom. ► Read more

Enriching acoustic representation for low resource languages

Date: 21/06/2024
Hour: 14:00
Localisation: IC2, salle des conseils
Speaker(s): Yannick Yomie Nzeuhang

Yannick Yomie Nzeuhang, PhD student at université de Yaoundé 1 and currently at Lium for a 3 month ESPERANTO secondment will be presenting his work on Friday 21 June at 2pm in the boardroom. ► Read more

Extend self supervised representation models with features engineering for NLP of African Languages

Date: 13/06/2024
Hour: 14:00
Localisation: IC2, salle des conseils
Speaker(s): Paulin Mélatagia

Paulin Melatagia, from the University of Yaoundé 1, who is currently on secondment as part of the Esperanto project, will talk to us about his current work, mainly on under-resourced languages. Thursday 13 June at 2pm. ► Read more

How to use multilingual embeddings for LRL(Low resources Languages)

Date: 31/05/2024
Hour: 14:00
Localisation: IC2, salle des conseils
Speaker(s): Martin Atangana Ongolo

Martin Atangana, PhD student at université de Yaoundé 1 and currently at Lium for a 3 month ESPERANTO secondment will be presenting his work on Friday 31 May at 2pm in the boardroom. ► Read more

Prosody seen from the angle of semantic relations: the case of the imitative voice of words

Date: 17/05/2024
Hour: 10:OO
Localisation: IC2, salle des conseils
Speaker(s): Antoine Tholly,

Antoine Tholly, currently on a post-doctoral contract at LIUM with Jane Wottawa in the DIETS project, will be presenting his thesis work on Friday 17 May at 10am in the boardroom. ► Read more

Robustness of speaker recognition systems: additive noise, reverberation, and linguistic content variabilities

Date: 05/04/2024
Hour: 10:15
Localisation: IC2, salle des conseils
Speaker(s): Mohammad Mohammadamini

Aran Mohammadamini, postdoc fellow at LIUM, will be presenting his research work during a team seminar on Friday 05 April at 10.15 am in the IC2 boardroom. ► Read more

Automatic translation of speech into pictograms to facilitate communication for people with language disabilities

Date: 22/03/2024
Hour: 10:15
Localisation: IC2, salle des conseils
Speaker(s): Cécile Macaire

Cécile Macaire, a PhD student in the GETALP team at the LIG under the supervision of Benjamin Lecouteux, will be presenting her research work during a team seminar on Friday 22 March at 10.15 am in the IC2 boardroom. ► Read more

To [h] or not to [h]? L2 production of /h/ in semi-spontaneous speech by French leaners of English and of German.

Date: 15/03/2024
Hour: 10:15
Localisation: IC2, salle des conseils
Speaker(s): Jane Wottawa

The seminar of the day is given by Jane Wottawa, lecturer at the LIUM and in the Department of Literature on her work. ► Read more

Emmanuel Blanchard's Reserach work presentation

Date: 20/02/2024
Hour: 10h00
Localisation: Le Mans - Laval
Speaker(s): Emmanuel Blanchard

Life, universe and the rest ► Read more

Seminar of Jeffrey Wiseman on innovation in medical edication

Date: 13/02/2024
Hour: 14h30
Localisation: IUT de Laval
Speaker(s): Jeffrey Wiseman

Innovation in medical education: from today's simulation centers to tomorrow's. ► Read more

Automatic annotation and classification of terminality for the description of interruptions in audiovisual media content

Date: 24/01/2024
Hour: 14:00
Localisation: IC2, salle des conseils
Speaker(s): Rémi Uro

The LIUM welcomes Rémi Uro, a PhD student at INA, who will present part of his thesis work. ► Read more

When neural speech technologies encounter non-conventional data: A discussion on speech recognition and speech synthesis

Date: 19/01/2024
Hour: 10:15
Localisation: IC2, salle des conseils
Speaker(s): Aghilas Sini

Today's seminar is given by Aghilas Sini, Senior Lecturer at the LIUM, on his previous work. ► Read more

Presentation of Raquel COELHO on AI for Education

Date: 16/01/2024
Hour: 10h
Localisation: visio
Speaker(s): Raquel COELHO

Emerging Computational Language Technologies in Higher Education: Insights from Biology and Computer Science ► Read more

Overview of speech-related topics at ADASP (Télécom Paris) and overseas

Date: 27/11/2023
Hour: 14h00
Localisation: Saint Denis D'orques
Speaker(s): Mathieu Fontaine

The LIUM welcomes Mathieu Fontaine, researcher at Télécom Paris. He'll discuss three recent projects: two conducted with Télécom Paris students and another in collaboration with the RIKEN Artificial Intelligence Project (AIP) Sound Scene Understanding (SSU) team in Japan. ► Read more

LST-Days

Date: 27/11/2023
Hour: 14h00
Localisation: Saint Denis D'orques
Speaker(s): Mathieu Fontaine, Adrien Bardet

The members of the LST team got away from it all for 2 days of intensive seminars and project presentations. We were also able to enjoy the seminars given by two external guests, Mathieu Fontaine, from Telecom Paris and Adrien Bardet, from Atlantique Traduction, many thanks to them. ► Read more

Perception of speech and music through a cochlear implant or simulations of cochlear implants (channel vocoders): Principles of operation, sound illustrations and perceptual data

Date: 24/11/2023
Hour: 10:OO
Localisation: IC2, salle des conseils
Speaker(s): Olivier Crouzet

The LIUM welcomes Olivier Crouzet, researcher at the Laboratoire de Linguistique de Nantes (LLING).
Elisabeth Delais-Rousserie and one of their students, Pascal Yapo, will also be present. Please note that the seminar will take place 1 hour earlier than usual. The seminar will take place in the boardroom of the IC2 building. ► Read more

Séminaire de Benjamin GEORGES sur l'IA pour la reconnaissance d'objet automatique

Date: 28/11/2023
Hour: 9h30
Localisation: Salle de conseil à Laval et visio
Speaker(s): Benjamin GEORGES

Séminaire de Benjamin GEORGES sur l'IA pour la reconnaissance d'objet automatique ► Read more

Prosody of Nigerian pidgin: corpus approach and experimental validation with a text-to-speech system

Date: 20/10/2023
Hour: 11h00
Localisation: IC2, salle des conseils
Speaker(s): Emmett Strickland & Marc Evrard
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

The next LST seminars will be given by Emmett Strickland (MoDyCo) in person and Marc Evrard (LISN) remotely and will be entitled respectively :
"Prosody of Nigerian pidgin: corpus approach and experimental validation with a text-to-speech system" et
"Annotation and proposed alternative to annotation for automatic detection of expressive speech". ► Read more

Séminaire d'Anne DASTUGUE sur la naissance du flow VR

Date: 17/10/2023
Hour: 10h
Localisation: Salle de conseil à Laval et visio
Speaker(s): Anne DASTUGUE

Séminaire d'Anne DASTUGUE. ► Read more

Co-designing intelligent systems that can enrich inclusive pictorial communication

Date: 12/06/2023
Hour: 11h00
Localisation: IC2, salle des conseils
Speaker(s): Laurianne Sitbon

Laurianne is a Future Fellow of the Australian Research Council (ARC), and Associate Professor in the school of Computer Science at the Queensland University of Technology (QUT) in Brisbane. Her seminar is entitled "Co-designing intelligent systems that can enrich inclusive pictorial communication" ► Read more

CI/CD, DevOps and Containers: A Winning Trio

Date: 09/06/2023
Hour: 14h00
Localisation: IC2, amphithéâtre
Speaker(s): Fethi Bougares

Fethi Bougares, a teacher-researcher at the LIUM on secondment to ElyaData, is currently at the lab as part of ESPERANTO. He will be giving a seminar on his work at Elyadata on 9 June at 2pm in the amphitheatre of the IC2 building. ► Read more

DEFT 2023 & Blizzard 2023

Date: 02/06/2023
Hour: 11h00
Localisation: IC2, salle des conseils
Speaker(s): LST

On Friday 2 June at 11am in the boardroom, we will be holding a double seminar on the latest evaluation campaigns (after IWSLT) in which the team has participated. ► Read more

ON-TRAC consortium systems for the IWSLT 2023 dialectal and low-resource speech translation tasks

Date: 26/05/2023
Hour: 11h00
Localisation: IC2, salle des conseils
Speaker(s): Hugo Riguidel

Hugo Riguidel, PhD student at LIUM, will present his research work during a seminar entitled "ON-TRAC consortium systems for the IWSLT 2023 dialectal and low-resource speech translation tasks". ► Read more

Sparser is better: one step closer to word embedding interpretability

Date: 12/05/2023
Hour: 11h00
Localisation: IC2, salle des conseils
Speaker(s): Thibault Prouteau & Simon Guillot

Simon Guillot and Thibault Prouteau, PhD students at LIUM, will present their research work during a seminar entitled "Sparser is better: one step closer to word embedding interpretability". ► Read more

Automatic translation for the Ewondo language, Automatic speech recognition for the Ewondo language

Date: 28/03/2023
Hour: 14h00
Localisation: en ligne
Speaker(s): Martin Rodrigue Atangana Ongolo et Yannick Yomie Nzeuhang
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Martin Rodrigue Atangana Ongolo and Yannick Yomie Nzeuhangi, PhD students at the University of Yaoundé 1 and currently in secondment at the University of Grenoble Alpes in the framework of ESPERANTO, will present their research work during seminars entitled "Automatic translation for the Ewondo language" and "Automatic speech recognition for the Ewondo language". ► Read more

Séminaire de Damien BRUN sur les Interfaces Humain-Machine

Date: 14/03/2023
Hour: 10
Localisation: Salle de réunion CERIUM Laval et visio
Speaker(s): Damien BRUN

Séminaire de Damien BRUN ► Read more

Qualitative Evaluation of Language Model Rescoring in Automatic Speech Recognition

Date: 20/01/2023
Hour: 10h00
Localisation: IC2, salle des conseils
Speaker(s): Thibault Roux

The next LST seminar will be given by Thibault Rouxi, PhD student at LS2N, LIA and LIUM and will be entitled "Evaluation of Language Model Rescoring in Automatic Speech Recognition". ► Read more

Report on the "Jean Zay" training course

Date: 06/01/2023
Hour: 11h00
Localisation: IC2, salle des conseils
Speaker(s): Mano Brabant

The next LST seminar will be given by Mano Brabant, PhD student at LIUM, who will present his advances on explicability and give us a feedback on the training he followed at Jean Zay last December. ► Read more

Anticipation of end of speech turn for interruption detection

Date: 09/12/2022
Hour: 11h00
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Rémi Uro

The next LST seminar will be given by Rémi Uro, PhD student at INA and will be entitled "Anticipation of end of speech turn for interruption detection". ► Read more

End-to-end model for named entity recognition from speech without paired training data

Date: 25/11/2022
Hour: 11h00
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Salima Mdhaffar
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Next LST seminar will be given by Salima Mdhaffar, postdoc at LIA (Avignon Université) and will address "End-to-end model for named entity recognition from speech without paired training data" ► Read more

Presentation on the preregistration method for sientific experimentations

Date: 29/11/2022
Hour: 15h30
Localisation: Zoom
Speaker(s): Estefanya Charlotte Vazquez Casaubon, PhD student from Ghent University

Preregistration is the practice of registering the hypotheses, methods, and/or analyses of a scientific study before it is conducted. It’s «emergence » in diverse disciplines has gained prominence within the open science community as a solution to some issues of the replication crisis (research practices, including p-hacking, publication bias, data dredging, inappropriate forms of post hoc analysis, and HARKing). But pre-registration has other advantages, including self-reflection of own research, credibility, among other. ► Read more

Extension of the bandwidth for voice signals captured by noise-proof microphones

Date: 10/11/2022
Hour: 11h00
Localisation: IC2, amphithéâtre
Speaker(s): Julien Hauret
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Next LST seminar will be given by Julien Hauret, PhD students at LMSSC (CNAM de Paris) and will address "Extension of the bandwidth for voice signals captured by noise-proof microphones" ► Read more

Séminaire de Jérome LEHUEN

Date: 18/10/2022
Hour: 9h
Localisation: Salle de réunion CERIUM Laval et visio
Speaker(s): Jérome LEHUEN
URL: https://univ-lemans-fr.zoom.us/j/82282859215?pwd=cEk4SUFQaldnOThiMlhNazVFdGlCUT09

ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks / Overlapped speech and gender detection with WavLM pre-trained features

Date: 14/10/2022
Hour: 11h00
Localisation: IC2 salle de cours
Speaker(s): Valentin Pelloin et Martin Lebourdais

Next LST seminar will be given by Valentin Pelloin and Martin Lebourdais, PhD students at LIUM and will address "ASR-Generated Text for Language Model Pre-training Applied to Speech Tasks" and "Overlapped speech and gender detection with WavLM pre-trained features" respectively. ► Read more

Apprentissage de représentations pour l'enseignement de la programmation

Date: 13/07/2022
Hour: 14h
Localisation: Salle de réunion CERIUM Laval et visio
Speaker(s): Guillaume Cleuziou

L'utilisation de plates-formes de validation de programmes est de plus en plus fréquente pour l'apprentissage des bases de l'informatique. Si l'automatisation des tests de validation libère du temps pour l'enseignant et ludifie le parcours de l'apprenant, on observe également certains biais induits par ces dispositifs pédagogiques. Des recherches en Intelligence Artificielle (IA) visent à pallier certains de ces biais. Pour cela, elles se heurtent au problème de l'analyse fine de ces programmes par les algorithmes d'apprentissage automatique. Dans cet exposé nous présentons une nouvelle méthode d'apprentissage de représentations de programmes (embeddings). Dans une approche centrée 'enseignant', nous proposons également quelques usages possibles de ces représentations pour la détection automatique de réponses. ► Read more

Evaluation of weakly-supervised methods for aspect extraction

Date: 01/07/2022
Hour: 10h30
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Mohamed Ettaleb
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Next LST seminar will be given by Mohamed Ettaleb, Post-doctoral fellow at LIUM and will address "Evaluation of weakly-supervised methods for aspect extraction". ► Read more

Am I collaborating well? Towards Automatic Collaboration Quality Detection Using Speech and Network Analytics.

Date: 05/07/2022
Hour: 10h
Localisation: Salle de réunion CERIUM Laval et visio
Speaker(s): Sambit PRAHARAJ
URL: https://sambitpraharaj.com/

Collaboration is a 21st century super skill. The detection of collaboration quality can help to support collaboration. This presentation addresses the automatic collaboration quality detection in a face-to-face setting in 3 different steps by summarizing my doctoral thesis: (1) to define the components to detect collaboration quality using audio data; (2) to explain the design of a sensor-based set up for automatic collaboration analytics using natural language processing, topic modelling, speech content analytics and learning analytics measures; (3) to move towards quantifying the quality of collaboration by using the automatic collaboration analytics set up and show these analysis using meaningful visualizations on an interactive dashboard consisting of network graphs. In addition to it, we address the challenges and issues at hand and how can solutions be built upon the work already done in this doctoral thesis. ► Read more

Overlapping speech and gender, a study of annotations for audiovisual media.

Date: 06/05/2022
Hour: 11h00
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Martin Lebourdais
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Next LST seminar will be given by Martin Lebourdais, PhD student at LIUM and will address "Overlapping speech and gender, a study of annotations for audiovisual media.". ► Read more

Trees, knights and puppets: transfer learning for processing of historical languages

Date: 29/04/2022
Hour: 11h00
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Loïc Grobol
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Next LST seminar will be given by Loïc Grobol, Assistant Professor at Université Paris Nanterre and will address "Trees, knights and puppets: transfer learning for processing of historical languages". ► Read more

Quality Estimation: Application to Machine Translation

Date: 15/04/2022
Hour: 11:00
Localisation: IC2, Salle des conseils
Speaker(s): Frédéric Blain
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

The next LST seminar will be presented by Frédéric Blain, lecturer at University of Wolverhampton and will be entitled "Quality Estimation: Application to Machine Translation". ► Read more

Les Actualités Françaises (1945-1969): the cinema of the event.

Date: 01/04/2022
Hour: 11h00
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Franck Mazuet
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

The next LST seminar will be presented in the framework of the Antract project by Franck Mazuet, filmmaker and researcher at the CHS-CNRS (Centre d'Histoire Sociale du XXé siècle) and will be entitled "Les Actualités Françaises (1945-1969): The cinema of the event". ► Read more

Multimodal Reasoning: Datasets, Models, and even some commonsense?

Date: 04/03/2022
Hour: 11h00
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Peter Vickers
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Next LST seminar will be given by Peter Vickers, PhD student in Sheffield and will address .Multimodal Reasoning: Datasets, Models, and even some commonsense. ► Read more

Quelle sera la place future de la Réalité Etendue dans la collaboration et l’apprentissage ?

Date: 01/03/2022
Hour: 10h
Localisation: salle de conseil IC2 et visio
Speaker(s): Corentin Coupry

La popularisation du terme Metavers en octobre 2021 et la facilité d’accès aux nouvelles technologies de Réalité Etendue (XR) ont fait entrer les mondes virtuels dans le domaine public. De nombreuses industries s’intéressent déjà à ces technologies pour la formation de leurs collaborateurs et pour faciliter la collaboration inter-métier. Le secteur de l’éducation pourrait également bénéficier de ces nouveaux mondes en adaptant ses méthodes pour tirer parti des possibilités offertes par ce concept. Durant ce séminaire, nous observerons quelques applications actuelles des technologies de XR pour la formation et la collaboration dans différents domaines (médical, industriel, …) afin d’ouvrir une réflexion sur les avantages que ces technologies pourraient apporter à la pédagogie de demain. ► Read more

Privacy-Preserving Speech Representation Learning using Vector Quantization

Date: 14/01/2022
Hour: 11h00
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Pierre Champion
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Next LST seminar will be given by Pierre Champion, Phd student at INRIA of Nancy and LIUM and will address "Privacy-Preserving Speech Representation Learning using Vector Quantization" ► Read more

Summarising Historical Text in Modern Languages

Date: 07/01/2022
Hour: 11h00
Localisation: online
Speaker(s): Chenghua Lin
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Next LST seminar will be given remotly by Chenghua Lin, lecturer at the University of Sheffield and will address "Summarising Historical Text in Modern Languages" ► Read more

Extending the study of speech accommodation: the relationship between hypospeech and speakers’ social proximity.

Date: 03/12/2021
Hour: 11h00
Localisation: IC2 salle de cours, en ligne
Speaker(s): Mélanie Lancien
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Next LST seminar will be given by Mélanie Lancien, from the university of Lausanne and will address "Extending the study of speech accommodation: the relationship between hypospeech and speakers’ social proximity" ► Read more

Research Careers

Date: 26/11/2021
Hour: 14h00
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Sylvain Meignier
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

The next LST seminar, presented by Sylvain Meignier, will focus on "careers in research". ► Read more

Non-Parametric Subspace Models for Acoustic Units Discovery

Date: 12/11/2021
Hour: 11h30
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Lucas Ondel
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Lucas Ondel defended his PhD at Brno and is now in Post-Doc at Université Paris-Saclay. He will present his work on Friday 12/11 at 11:30. ► Read more

How the research works

Date: 15/10/2021
Hour: 11h00
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Anthony Larcher
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Anthony Larcher will introduce some technical aspects of how research is done today. ► Read more

Conférence de Cendrine MERCIER, CREN

Date: 19/10/2022
Hour: 10h
Localisation: salle de conseil IC2 et visio
Speaker(s): Cendrine MERCIER

Cendrine MERCIER est Maitre de Conférences au CREN. Elle est également référente numérique des 5 INSPE de l'Académie de Nantes. ► Read more

LST day

Date: 01/10/2021
Hour: 9h00 - 17h00
Localisation: IC2 salle de cours, en ligne
Speaker(s): LST team

On October 1st, the day of the LST team takes place. On this occasion, researchers - the young and the more experienced - present their research themes. ► Read more

A recommendation approach based on data mining and multi-layer labeled graphs.

Date: 01/10/2021
Hour: 14h00
Localisation: IC2 salle de cours, en ligne
Speaker(s): Mohamed Ettaleb
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

A recommendation approach based on data mining and multi-layer labeled graphs.  

The objective of a recommendation system is to assist users in choosing relevant items from a large set of elements. In the current context of the boom in the number of academic publications available (books, articles, etc.) online, providing a personalized recommendation service becomes a necessity.

► Read more

Les algorithmes font-ils la loi ?

Date: 18/10/2021
Hour: 10h30
Localisation: Espace Mayenne, Laval
Speaker(s): Aurélie JEAN
URL: http://www.univ-lemans.fr/fr/actualites/agenda2021/octobre-2021/conference-de-rentree-chaire-droit-transitions-societales.html

Aurélie Jean nous entraîne dans un nouveau voyage : au cœur de nos institutions juridiques et des algorithmes qui s’y exercent. Comment la loi est-elle pensée et appliquée au temps des algorithmes ? Comment les algorithmes sont-ils utilisés au sein du système judiciaire ? Et est-il vraiment possible de les réguler ? ► Read more

The protection of personal data in the era of the RGPD

Date: 17/09/2021
Hour: 11h00
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Félicien Vallet
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Personal data protection in the era of the RGPD  

The CNIL is the authority in charge of personal data protection in France.This presentation will review the birth of the CNIL in 1978, explain how it works and the legal framework on which it is based, and explore more specifically certain subjects on which it is currently very much in demand, in particular biometrics and artificial intelligence.

► Read more

Explicability and Interpretability of AI models: concepts, approaches and adaptability to the domain of speech processing

Date: 03/09/2021
Hour: 14h00
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Jean-François Bonastre
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Explicability and Interpretability of AI models: concepts, approaches and adaptability to the domain of speech processing  

This presentation proposes to define the notions of explicability and interpretability in AI and to give an overview of the approaches used. The approaches are explored depending on their context in the processing toolchain and the type of information they consider.

► Read more

Joint effort on data loading process and its application to VAD, speaker turn detection and overlap detection

Date: 18/06/2021
Hour: 11h00
Localisation: IC2 salle des conseils, en ligne
Speaker(s): Martin Lebourdais, Théo Mariotte
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

Joint effort on data loading process and its application to VAD, speaker turn detection and overlap detection  

Diarization is the task of finding “Who spoke when?” in an audio stream. It relies on two subtasks defined as segmentation and clustering. The former most often includes voice activity detection (VAD), overlapped speech detection (OSD) and speaker change detection (SCD). This work introduces a data loading process (DataLoader) to format and distribute the speech segments used for the training of these three tasks.

► Read more

Human assisted speaker diarization, approach and demonstrator

Date: 21/05/2021
Hour: 11h00
Localisation: online
Speaker(s): Meysam Shamsi, Yevhenii Prokopalo and Anthony Larcher
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

The diarization team including students from ENSIM will present their work on Friday, 21th at 11:00. ► Read more

End2End Acoustic to Semantic Transduction

Date: 12/05/2021
Hour: 11h00
Localisation: online
Speaker(s): Valentin Pelloin
URL: https://univ-lemans-fr.zoom.us/j/92143709904?pwd=Qy9QTXUydExNSlFnS0pWY0ZaNXpzUT09

End2End Acoustic to Semantic Transduction  

We propose a novel end-to-end sequence-to-sequence spoken language understanding model using an attention mechanism. It reliably selects contextual acoustic features in order to hypothesize semantic contents.

► Read more

SINr: fast computing of Sparse Interpretable Node Representations is not a sin!

Date: 19/04/2021
Hour: 11h00
Localisation: Online
Speaker(s): Thibault Prouteau
URL: https://univ-lemans-fr.zoom.us/j/92384843807?pwd=Rko2SVdoMzVqcTlzRG85Qk1GZ01PUT09

SINr: fast computing of Sparse Interpretable Node Representations is not a sin!

 

While graph embedding aims at learning low-dimensional representations of nodes encompassing the graph topology, word embedding focus on learning word vectors that encode semantic properties of the vocabulary. The first finds applications on tasks such as link prediction and node classification while the latter is systematically considered in natural language processing. Most of the time, graph and word embeddings are considered on their own as distinct tasks. However, word co-occurrence matrices, widely used to extract word embeddings, can be seen as graphs.

► Read more

MiniBERT: a simple and explainable BERT model

Date: 12/03/2021
Hour: 11h00
Localisation: Online
Speaker(s): Gaëtan Caillaut
URL: https://univ-lemans-fr.zoom.us/j/93981603627?pwd=NjcwZDYvUU5sTjlzaTcvMEd5bWZ0Zz09

MiniBERT: a simple and explainable BERT model  

As part of the PolysEmY project, we work with the SNCF (French railway company) to produce "polysemic-aware" word embeddings.

► Read more

Multilingual neural architectures for natural language processing

Date: 19/02/2021
Hour: 11h00
Localisation: IC2, visio conférence
Speaker(s): Adrien Bardet
URL: https://univ-lemans-fr.zoom.us/j/93938372404?pwd=ZENaeWhuRVUwQzJKdVl4c0RSbkhGZz09

Multilingual neural architectures for natural language processing

 

Machine translation using little data leads to poor performance. The use of multilingual systems is one solution to this problem. Multilingual machine translation systems make it possible to translate several languages within the same system. They allow languages with little data to be learned alongside languages with more data, thus improving the performance of the translation system. This thesis focuses on multilingual machine translation approaches to improve performance for languages with limited data. I have worked on several multilingual translation approaches based on different transfer techniques between languages. The different approaches proposed, as well as additional analyses, have revealed the impact of the relevant criteria for transfer. They also show the importance, sometimes neglected, of the balance of languages within multilingual approaches.

► Read more

Are learning analytics doomed to failure?

Date: 22/01/2021
Hour: 11h00
Localisation: Online
Speaker(s): Rémi Venant
URL: https://zoom.us/j/91854530429?pwd=WWV0OWEzV3ZsbnFLdHorVTdWb25pdz09

Les learning analytics seraient-elles promises à l'échec ?

 

learning analytics (LA) are undergoing increasing development, and following the COVID-19 pandemic and the forced introduction of large-scale distance learning, it is reasonable to anticipate an acceleration in the introduction of hybrid practices and therefore a growing need for LA. However, due to an increase in their intrinsic complexity, particularly through the use of increasingly advanced statistical models and artificial intelligence (AI) techniques, they are struggling to be put into production in a real learning context. Improving the explainability of AIs for non expert users in data analysis is therefore a crucial issue for Technology Enhanced Learning.

► Read more