Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings

Marcely Zanon (1) , Bolaji Yusuf (2, 3) , Lucas Ondel (2) , Aline Villavicencio (4, 5) , Laurent Besacier (1, 6)

1 LIG - Laboratoire d'Informatique de Grenoble
2 FIT / BUT - Faculty of Information Technology [Brno]
3 Boǧaziçi üniversitesi = Boğaziçi University [Istanbul]
4 University of Sheffield [Sheffield]
5 FEDERAL UNIVERSITY OF RIO GRANDE DO SUL PORTO ALEGRE BRA
6 Naver Labs Europe [Meylan]

Domaines: Apprentissage [cs.LG]; Informatique et langage [cs.CL]

Marcely Zanon, Bolaji Yusuf, Lucas Ondel, Aline Villavicencio, Laurent Besacier. Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings. 2021. ⟨hal-03477951⟩