no code implementations • BigScience (ACL) 2022 • Nicolas Hervé, Valentin Pelloin, Benoit Favre, Franck Dary, Antoine Laurent, Sylvain Meignier, Laurent Besacier
This papers aims at improving spoken language modeling (LM) using very large amount of automatically transcribed speech.
no code implementations • LREC 2022 • Gaëlle Laperrière, Valentin Pelloin, Antoine Caubrière, Salima Mdhaffar, Nathalie Camelin, Sahar Ghannay, Bassam Jabaian, Yannick Estève
In this paper, we focus on the French MEDIA SLU dataset, distributed since 2005 and used as a benchmark dataset for a large number of research works.
no code implementations • LREC 2022 • Salima Mdhaffar, Valentin Pelloin, Antoine Caubrière, Gaëlle Laperriere, Sahar Ghannay, Bassam Jabaian, Nathalie Camelin, Yannick Estève
Pretrained models through self-supervised learning have been recently introduced for both acoustic and language modeling.
no code implementations • 11 Oct 2022 • Gaëlle Laperrière, Valentin Pelloin, Mickaël Rouvier, Themos Stafylakis, Yannick Estève
In this paper we examine the use of semantically-aligned speech representations for end-to-end spoken language understanding (SLU).
no code implementations • 5 Jul 2022 • Valentin Pelloin, Franck Dary, Nicolas Herve, Benoit Favre, Nathalie Camelin, Antoine Laurent, Laurent Besacier
We aim at improving spoken language modeling (LM) using very large amount of automatically transcribed speech.
no code implementations • 1 Feb 2021 • Valentin Pelloin, Nathalie Camelin, Antoine Laurent, Renato de Mori, Antoine Caubrière, Yannick Estève, Sylvain Meignier
In this paper, we propose a novel end-to-end sequence-to-sequence spoken language understanding model using an attention mechanism.
no code implementations • JEPTALNRECITAL 2020 • Valentin Pelloin, Thibault Prouteau
Pour r{\'e}pondre {\`a} cette question, nous consid{\'e}rons deux corpus en langue de sp{\'e}cialit{\'e} : O HSUMED issu du domaine m{\'e}dical, et un corpus de documentation technique, propri{\'e}t{\'e} de SNCF.