Multi-lingual Speech to Speech Translation for Under-Resourced Languages

Anthony Larcher (1) , Yannick Estève (2) , Mickael Rouvier (2) , Natalia Tomashenko (2) , Jarod Duret (2) , Gaelle Laperriere (2) , Santosh Kesijaru (3) , Marek Sarvas (3) , Renata Kohlova (3) , Henry Li (4) , Antoine Laurent (1) , Thibault Gaudier (1) , Valentin Pelloin (1) , Thomas Thebaud (5) , Emmanuelle Billard (1) , Olivier Galibert (6) , Swen Ribeiro (7) , Harshita Diddee (8) , Sameer Khurana (9) , Laurent Besacier (10) , Ioan Calapodescu (10) , Themos Stafylakis (11) , Tomas Pavliceck (12) , Cecile Macaire (13) , Alejandro Ciuba (14) , Peter Vickers (15) , Luis Vicente (16) , Victoria Mingote (16) , Pablo Gimeno (16)

1 LIUM - Laboratoire d'Informatique de l'Université du Mans
2 LIA - Laboratoire Informatique d'Avignon
3 BUT - Brno University of Technology [Brno]
4 JHU - Johns Hopkins University
5 Orange Labs R&D [Rennes]
6 LCM-CNAM - Laboratoire commun de métrologie LNE-CNAM
7 LNE - Laboratoire National de Métrologie et d’Essais
8 Microsoft Research
9 MIT CSAIL - MIT Computer Science & Artificial Intelligence Lab
10 Naver Labs Europe [Meylan]
11 Omilia
12 Phonexia s. r. o. (Phonexia s. r. o.)
13 LIG - Laboratoire d'Informatique de Grenoble
14 PITT - University of Pittsburgh
15 University of Sheffield [Sheffield]
16 I3A - Aragón Institute of Engineering Research [Zaragoza]

This report describe the research done during the first ESPERANTO/JSALT workshop from the 13th June 2022 to the 5th of August 2022.

Mots clés: Speech processing; speech-to-speech translation

Domaines: Intelligence artificielle [cs.AI]

Anthony Larcher, Yannick Estève, Mickael Rouvier, Natalia Tomashenko, Jarod Duret, et al.. Multi-lingual Speech to Speech Translation for Under-Resourced Languages. Le Mans Université. 2022. ⟨hal-04176910⟩