"Audio-Visual Speech Recognition is Worth 32×32×8 Voxels."

Dmitriy Serdyuk, Otavio Braga, Olivier Siohan (2021)

Details and statistics

DOI:

access: open

type: Informal or Other Publication

metadata version: 2021-09-27

a service of  Schloss Dagstuhl - Leibniz Center for Informatics