[molasses]

I'm able bodied, but years back suffered tremendous pain, that led to me having to lie down on my back and use the computer with a keyboard. And TBH even that was a pain. I got quite far under OSX tiger, and browse the web. Use a terminal etc. But at the time it led me into thinking about alternative interfaces. And the one thing that did catch my eye was 'dasher' for text entry. Which could be controlled with a simple pointer. And it did make me wonder how far you could go with a pointer based interface. I wasn't that fast while trying it out. But could construct sentences with a bit of effort.

https://www.inference.org.uk/dasher/

I've been thinking about it some more recently, as AI could assist with word completion, and augmenting it with some AI helpers could really improve things. And if the idea was extended.

Not wanting to sound like an able-ist snob, but interfacing with traditional computers with a keyboard is hard. And the interface is clumsy. Even touch devices and keyboards. My Mum could never use a computer, but she has worked out how to use a tablet and find videos on Youtube. I keep meaning to introduce her to voice input. As this would really benefit her.

Despite the huge tech leaps with smartphones and tablets and what not, I do feel there has been a huge regression in basic communication between people only exacerbated by the pandemic. There's knowledge available easily at people's fingertips and that's great, along with new channels of communication. But text based comms have retarded many people.

[lachlan_gray]

Since when we talk, our tongues tap patterns on the roof of the mouth and the back of the teeth, I wonder if AI processing could infer what words you are shaping from these sensors. Maybe it’s possible to input text by mouthing words silently, but without opening your mouth. Kind of like how it’s possible to eavesdrop from just the sound of keyboard clicks:

https://github.com/ggerganov/kbd-audio

[dmreedy]

Tongue contact might be sufficient (in linguistics, two of the axes of "pronunciation space" are "dental" (whether the tongue makes contact with the teeth) and "palatal" (whether the tongue makes contact with the palate).

There are a number of other dimensions however that are equally important in the creation of word-sounds (e.g., whether the lips are pursed, whether the vocal folds are vibrating, whether the teeth make contact with the lips, where the tongue is located in the space of the mouth [for vowels], etc) and would make determination just from the dental/palatal axes pretty difficult I think. But maybe with enough context, you could get something predictive that is more than good enough, even if it's not into deterministic territory

[6177c40f]

I think you're talking about subvocal recognition [1]. People are indeed using ML for it, but it looks like it's more complicated than it appears. Still, I think it's only a matter of time before it's available to the average consumer, which I can't wait for because I've wanted something like this for a long time. I do my best thinking when I'm hiking, and I'd love to be able to dictate my thoughts on the move without looking like I'm talking to myself out loud (even though I am, I guess) in public.

[1] https://en.wikipedia.org/wiki/Subvocal_recognition

[jlundberg]

Dasher is really fun!

Remember playing a lot with it back when it was released. Left a lasting impression and broadend my view on input mechanisms.