"Audio-Visual Speech Recognition is Worth $32\times 32\times 8$ Voxels."

Dmitriy Serdyuk, Otavio Braga, Olivier Siohan (2021)

Details and statistics

DOI: 10.1109/ASRU51503.2021.9688191

access: closed

type: Conference or Workshop Paper

metadata version: 2022-02-09

a service of  Schloss Dagstuhl - Leibniz Center for Informatics