A new study suggests that VSR models could perform even better if they used additional available visual information.
This is a companion discussion for the article “Beyond Lipreading: Visual Speech Recognition Looks You in the Eye - https://medium.com/syncedreview/beyond-lipreading-visual-speech-recognition-looks-you-in-the-eye-4e7413518149” submitted on the community's news feed.
Reply to this topic to share your thoughts on this article.