"STEMM: Self-learning with Speech-text Manifold Mixup for Speech Translation."

Qingkai Fang et al. (2022)

Details and statistics

DOI: 10.48550/ARXIV.2203.10426

access: open

type: Informal or Other Publication

metadata version: 2023-10-24

a service of  Schloss Dagstuhl - Leibniz Center for Informatics