Natacha Miniconi

Optimizing Human Intervention for Synthetic Speech Quality Evaluation: Active Learning for AdaptabilityStarting: 01/10/2024PhD Student: Natacha MiniconiAdvisor(s): Anthony LarcherCo-advisor(s): Meysam ShamsiFunding: Region TandemContext: The primary objective of Text-to-Speech (TTS), speech conversion and speech to speech translation system is to synthesize or generate a high-quality speech signal. Typically, the quality of synthetic speech is subjectively evaluated by […]

TV2M-E

Multilingual Multimodal Voice Translation – Expressive (TV2M-E)Date: 06/2024 – 06/2026Funding: Région Pays de la LoireCall: PULSARURL: https://lium.univ-lemans.fr/en/tv2m-e/LIUM Participant(s): Aghilas SiniSummary A bilingual or polyglot speaker has the ability to communicate coherently in several languages, adapting to different contexts. Transferring this skill to machines could contribute to the preservation of cultural heritage by maintaining less privileged […]

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

Seminar from Anthony Larcher, Professor at LIUM   Date: 02/07/2024 Time: 10h00 Localization: IC2, Boardroom Speaker: Anthony Larcher     Trustworthy, explainable, interpretable… what can we expect for speech processing?   Improvements in the performance of automated systems have led to the widespread commercial deployment of applications that are still poorly understood. To ensure the […]

Soutenance de thèse : Thibault Prouteau

PhD defence, Thibault Prouteau Date : 03/07/2024 Time : 14h00 Location : Le Mans Université; IC2 buiding Auditorium   Title: Graphs, Words, and Communities: Converging Paths to Interpretability with a Frugal Embedding Framework   Jury members : Vincent LABATUT, Assistant Professor, Université d’Avignon, Reviewer Christine LARGERON, Professor, Université Jean Monnet, Saint-Étienne, Reviewer Cécile BOTHOREL, Assistant […]

Enrichir la représentation acoustique pour les langues faiblement dotées

Seminar from Yannick Yomie Nzeuhang, PhD student at Université Yaoundé 1 and ESPERANTO secondee at LIUM   Date: 21/06/2024 Time: 14h00 Localization: IC2, Boardroom Speaker: Yannick Yomie Nzeuhang     Enriching acoustic representation for for LRL(Low resources Languages)   A popular approach in the literature for tackling the task of speech recognition for low-resource languages […]

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

Seminare from Paulin Mélatagia, Université Yaoundé 1, ESPERANTO secondee at LIUM   Date: 13/06/2024 Time: 14h00 Localization: IC2, Boardroom Speaker: Paulin Mélatagia     Extend self supervised representation models with features engineering for NLP of African Languages   Most of the African languages are low-resourced and their linguistic characteristics are different from those of the […]

Comment utiliser les plongements multilingues pour les langues peu dotées

Seminar from Martin Atangana Ongolo, PhD student at Université Yaoundé 1 and ESPERANTO secondee at LIUM   Date: 31/05/2024 Time: 14h00 Localization: IC2, Boardroom Speaker: Martin Atangana Ongolo     How to use multilingual embeddings for LRL(Low resources Languages)   The aim of this seminar is to present the problem of mapping quality for Low […]

Matthieu François

Quantitative analysis of opposition to transition technologies on social networksStarting: 01/03/2024PhD Student: Matthieu FrançoisAdvisor(s): Xavier Arnauld de Sartre (Université de Pau)Co-advisor(s): Nicolas Dugué Funding: ANR Chaire industrielle REASONSDescription: This thesis aims to adopt data mining techniques to study commitments to ecological transition, and in particular to characterize the rise of debates on transition technologies on […]

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

Seminar from Aran Mohammadamini, Postdoctoral fellow at LIUM   Date: 05/04/2024 Time: 10h15 Localization: IC2, Boardroom Speaker: Mohammad Mohammadamini     Robustness of speaker recognition systems: additive noise, reverberation, and linguistic content variabilities   Speaker recognition systems authenticate the identity of speakers from their speech utterances. In order to authenticate the identity of a claimed […]