This work describes an interactive decoding method to improve the performance of visual speech recognition systems using user input to compensate for the inherent ambiguity of the task. Unlike most phoneme-to-word decoding pipelines, which produce phonemes and feed these through a finite state transducer, our method instead expands words in lockstep, facilitating the insertion of interaction points at each word position. Interaction points enable us to solicit input during decoding, allowing users to interactively direct the decoding process. We simulate the behavior of user input using an oracle to give an automated evaluation, and show promise for the use of this method for text input.
@article{arxiv.2107.00692,
title = {Interactive decoding of words from visual speech recognition models},
author = {Brendan Shillingford and Yannis Assael and Misha Denil},
journal= {arXiv preprint arXiv:2107.00692},
year = {2021}
}