15 votes

AlterEgo, a new wearable device system, can detect what you’re saying when you’re talking to yourself, even if you’re completely silent and not moving your mouth

6 comments

  1. [3]
    Adys Link
    Something feels off about this article. Either this is a scam, or even a tiny fraction of it is true and working in which case it's a way, way bigger deal than the article is making it to be.

    Something feels off about this article. Either this is a scam, or even a tiny fraction of it is true and working in which case it's a way, way bigger deal than the article is making it to be.

    7 votes
    1. [2]
      cfabbro (edited ) Link Parent
      The MIT media lab page for the project has more info if you want to go digging: https://www.media.mit.edu/projects/alterego/overview/ Which even includes a link to the related study: AlterEgo: A...

      The MIT media lab page for the project has more info if you want to go digging:
      https://www.media.mit.edu/projects/alterego/overview/

      Which even includes a link to the related study:
      AlterEgo: A Personalized Wearable Silent Speech Interface

      Abstract
      We present a wearable interface that allows a user to silently converse with a computing device without any voice or any discernible movements - thereby enabling the user to communicate with devices, AI assistants, applications or other people in a silent, concealed and seamless manner. A user's intention to speak and internal speech is characterized by neuromuscular signals in internal speech articulators that are captured by the AlterEgo system to reconstruct this speech. We use this to facilitate a natural language user interface, where users can silently communicate in natural language and receive aural output (e.g - bone conduction headphones), thereby enabling a discreet, bi-directional interface with a computing device, and providing a seamless form of intelligence augmentation. The paper describes the architecture, design, implementation and operation of the entire system. We demonstrate robustness of the system through user studies and report 92% median word accuracy levels.

      edit: I'm not nearly smart enough to completely parse the study, but it seems this is a nerve signal reading system and not a brain signal reading one though? So maybe their claims are not quite so outlandish?

      The system captures neuromuscular signals from the surface of the user's skin via a wearable mask.

      Unlike proposed traditional brain computer interfaces (BCI), such as head based EEG/fMRI/DOT/fNIRS, the platform does not have access to private information or thoughts and the input, in this case, is voluntary on the user's part. The proposed platform is robust on extended vocabulary sizes than traditional BCI since we propose a peripheral nerve interface by taking measurements from the facial and neck area, which allows for silent speech signals to be distilled without being accompanied by electrical noise from the frontal lobe of the cerebral cortex.

      5 votes
      1. moocow1452 Link Parent
        My understanding is that it reads the throat muscles, as those still fire off when you think in a monologue, hence the whole subvocalization issue that speed reading was a thing. It uses a sensor...

        My understanding is that it reads the throat muscles, as those still fire off when you think in a monologue, hence the whole subvocalization issue that speed reading was a thing. It uses a sensor to pick up on that, so technically it works with nerves, but it's more picking up on your vocal cords doing their thing, even when you're not speaking.

        5 votes
  2. tesseractcat Link
    I've seen pop sci articles and discussions about this device for years now, but nothing has really changed. There's still no update, dev kits, or even someone replicating the device. I bet that...

    I've seen pop sci articles and discussions about this device for years now, but nothing has really changed. There's still no update, dev kits, or even someone replicating the device. I bet that there's some technical issue with the device that they haven't been able to resolve yet that makes it impractical or inaccurate.

    6 votes
  3. moocow1452 Link
    I want this more than anything... With whatever neural tech in the future being invasive and me being a scatterbrained fool who can not write shit down or organize priorities, inviting a little...

    I want this more than anything... With whatever neural tech in the future being invasive and me being a scatterbrained fool who can not write shit down or organize priorities, inviting a little computer assistance to peek on my monologue, keep the good parts, or break me out of a brain cycle, that sort of power over myself is incredible.

    4 votes
  4. Hypersapien Link
    What's scary is that eventually someone is going to get stuff like this to work at range, like from across a room.

    What's scary is that eventually someone is going to get stuff like this to work at range, like from across a room.

    1 vote