I did research in this space about eight years ago. Our approach was to look at deformations in the ear canal. Rumor has it that Apple AirPods will have sensors in the ear canal. I was hoping to use those sensors with our app, but it looks like Apple is not going to provide access to the raw sensor data. I expected Apple is going to support subvocal speech pretty soon.
From my understanding decoding via ear deformation requires the mouthing to be quite exaggerated. I am also looking forward to Apple launching it soon though, hopefully it gets more people excited and aware about the category at least