"VCSE: Time-Domain Visual-Contextual Speaker Extraction Network."

Junjie Li et al. (2022)

Details and statistics

DOI: 10.48550/ARXIV.2210.06177

access: open

type: Informal or Other Publication

metadata version: 2023-03-24

a service of  Schloss Dagstuhl - Leibniz Center for Informatics