2 papers
cs.CV2024
Enhancing CTC-Based Visual Speech Recognition
Hendrik Laux, Anke Schmeink
This paper presents LiteVSR2, an enhanced version of our previously introduced efficient approach to Visual Speech Recognition (VSR). Building upon our knowledge distillation frame…
cs.CV2023
LiteVSR: Efficient Visual Speech Recognition by Learning from Speech Representations of Unlabeled Data
Hendrik Laux, Emil Mededovic, Ahmed Hallawa +3
This paper proposes a novel, resource-efficient approach to Visual Speech Recognition (VSR) leveraging speech representations produced by any trained Automatic Speech Recognition (…