Séminaire de Charles Guin-Vallerand

Conception et déploiement de technologies d’assistance pour le support à la cognition basées sur l’intelligence ambiante et la réalité mixte   Date: 31/03/2025 Time: 14h Place: Cerium, salle de réunion et en visio Speaker: Charles Guin-Vallerand Résumé : Ce séminaire présente les projets de recherche du Laboratoire DOMUS de l’Université de Sherbrooke (Canada), axés sur le […]

Using large ASR models for training lightweight models in low-resource and computation-limited languages

Seminar from Aran Mohammadamini, Post-doc fellow at LIUM   Date: 24/03/2025 Time: 11h00 Place: IC2, Boardroom Speaker: Aran Mohammadamini     Using large ASR models for training lightweight models in low-resource and computation-limited languages   Low-resource languages often suffer not only from a lack of language resources but also from limited computational resources. Recent multilingual […]

Advances in measuring the interpretability of speaker representation spaces

Seminar from Félix Saget, PhD student at LIUM   Date: 10/03/2025 Time: 11h00 Place: IC2, Boardroom Speaker: Félix Saget     Advances in measuring the interpretability of speaker representation spaces   Features extracted by speaker representation models have proven to be potent and versatile, yielding respectable performance in various speaker-related tasks. However, a human user […]

LT4ALL – Bridging Technology & Linguistic Diversity

Aghilas Sini attended the second edition of LT4ALL, an international conference organized by UNESCO, focusing on language technologies for low-resourced and indigenous languages. Over three intensive days, 200+ participants from ~50 countries—spanning academia, NGOs, industry, and governments—gathered to discuss how technology can support linguistic diversity and improve access to knowledge worldwide. 🔹 Day 1: Showcased […]

Atelier PLUME – outil de collecte d’analyse de trace en VR

Atelier PLUME   Date: 25/02/2025 Time: 9h Place: Cerium, salle d’éxpérimentation Speaker: Charles JAVERLIAT et Sophie VILLENAVE   PLUME est une boîte à outils logicielle libre (GPLv3) qui permet l’enregistrement exhaustif de données comportementales (y compris des données synchrones), leur relecture et leur analyse interactives hors ligne, et leur partage facile grâce à notre format de […]

Towards interpretable representations for audio and speech processing

Seminar from Théo Mariotte, lecturer at LIUM   Date: 24/02/2025 Time: 10h30 Place: IC2, Boardroom Speaker: Théo Mariotte     Towards interpretable representations for audio and speech processing   This seminar is divided into two main parts. The first part reviews my previous research, while the second explores future research directions. In the first section, […]

Information Extraction and Analysis from News videos

Seminar from Sadok Mansouri, ATER at LIUM   Date: 13/01/2025 Time: 10h00 Place: IC2, Boardroom Speaker: Sadok Mansouri     Information Extraction and Analysis from News videos   Information extraction from videos is an important research topic in content-based video indexing and retrieval. Indeed, the visual text present in news videos typically provides rich semantic […]

The Limits of Speech Systems: Navigating Adversarial and Poisoning Threats with Robust Defenses

Seminare from Thomas Thebaud, researcher at CLSP, JHU   Date: 18/12/2024 Time : 13h30 Place: IC2, Boardroom Speaker: Thomas Thebaud,     The Limits of Speech Systems: Navigating Adversarial and Poisoning Threats with Robust Defense   Summary: The widespread adoption of voice-controlled devices and speech recognition systems underscores the critical need for robust security measures […]

TTS for low resource languages, dialects and accents

TTS for low resource languages, dialects and accents (13/12/2024) Currently, many different neural architectures are available to use a Text-to-Speech (TTS) system on the shelf. However it is not always easy to choose the best network for a given application. Especially the limits and drawbacks of pre-trained models are not well defined. This can be […]