AlterEgo: Interfacing with devices through silent speech

942K views · 8 years ago · demo · dated

An MIT Media Lab demo of AlterEgo, a wearable that lets a person interface with devices through silent speech. It reads signals from the face while the wearer internally articulates words, with no audible speech.

HN people bring it up as a serious candidate for the next input method after the keyboard, a way to talk to computers without making a sound.

“made a headset that would read electrical impulses from your face”

4 comments from Hacker News

r
@rishabhd2018 · in “AlterEgo: Interfacing with devices through silent speech”
Submitted the video to Hacker News.
RecommendsView on HN
a
@alexryan2018 · in “AlterEgo: Interfacing with devices through silent speech”
Nice video of this: ▶ this video
RecommendsView on HN
a
@andai2023 · in “High-res image reconstruction with latent diffusion models from human brain”
There was a guy at MIT about ten years ago (edit: 2018! Woah) who made a headset that would read electrical impulses from your face. Apparently when people think in words, the same nerves fire as when they speak, just at a lower activation level. Using those signals it is possible to reconstruct the words being thought. I'm surprised it didn't seem to go anywhere. Edit: found it ▶ this video
a
@anotheryou2018 · in “Steven Sinofsky on iPads replacing laptops and transitions in computing”
I don't see it that black and white. The big difference between iPad and PC is the input. It's no surprise that consumers are less power users of input methods than people working on their machines. Power users always use less intuitive, but more efficient input. The mouse accelerates my cursor, it moves farther then the mouse travels and has great accuracy. On the iPad I'd have to stir my arm around all day and selecting within text with your finger in the way was never fun either (though the latter can be fixed easily). I could only imagine in "air mouse", like a touchpad on your desk with mouse-like tapping and scrolling per finger. Typing is where I see input methods might evolve. A touch-typists will remain more efficient, especially coding for a long time. Physical feedback on screen-keyboards would have to improve to the level of physical keyboards to fix that. Good speech to text (or mumble to text¹) might overtake the keyboard for prose but not for code unless the synax of programming languages adapts. After that I see eye-tracking and direct brain interfaces, but those wouldn't be iPad exclusive either. ¹ ▶ this video
CitesView on HN