Stories
Slash Boxes
Comments

SoylentNews is people

SoylentNews is powered by your submissions, so send in your scoop. Only 17 submissions in the queue.
posted by chromas on Wednesday August 07 2019, @07:19PM   Printer-friendly
from the voices-keep-telling-me-to-buy-stuff dept.

Submitted via IRC for AndyTheAbsurd

AlterEgo, [Arnav] Kapur's 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.

The technology involves a system of sensors that detect the minuscule neuromuscular signals sent by the brain to the vocal cords and muscles of the throat and tongue. These signals are sent out whenever we speak to ourselves silently, even if we make no sounds. The device feeds the signals through an A.I., which "reads" them and turns them into words. The user hears the A.I.'s responses through a microphone that conducts sound through the bones of the skull and ear, making them silent to others. Users can also respond out loud using artificial voice technology.

[...] Kapur is currently testing the device on people with communication limitations through various hospitals and rehabilitation centers in the Boston area. These limitations could be caused by stroke, cerebral palsy or neurodegenerative diseases like ALS. In the case of ALS, the disease affects the nerves in the brain and spinal cord, progressively robbing people of their ability to use their muscles, including those that control speech. But their brains still send speech signals to the vocal cords and the 100-plus muscles involved in speaking. AlterEgo can capture those signals and turn them into speech. According to Kapur's research[pdf], the system is about 92 percent accurate.

Source: https://www.smithsonianmag.com/innovation/device-can-hear-voice-inside-your-head-180972785/


Original Submission

This discussion has been archived. No new comments can be posted.
Display Options Threshold/Breakthrough Mark All as Read Mark All as Unread
The Fine Print: The following comments are owned by whoever posted them. We are not responsible for them in any way.
(1)
  • (Score: 0) by Anonymous Coward on Wednesday August 07 2019, @07:23PM

    by Anonymous Coward on Wednesday August 07 2019, @07:23PM (#877190)

    I don't like what it's saying.

  • (Score: 2) by Hartree on Wednesday August 07 2019, @07:43PM

    by Hartree (195) on Wednesday August 07 2019, @07:43PM (#877199)

    "Some people didn't like what the voice did say

    So I took the voice and I locked it away, I got the key, I got the key
    Voices, I hear voices, voices, I hear voices"

  • (Score: 0) by Anonymous Coward on Wednesday August 07 2019, @07:52PM

    by Anonymous Coward on Wednesday August 07 2019, @07:52PM (#877202)

    Cool, a M.A.N.T.I.S. for the voice!

  • (Score: 1, Interesting) by Anonymous Coward on Wednesday August 07 2019, @08:09PM (2 children)

    by Anonymous Coward on Wednesday August 07 2019, @08:09PM (#877206)

    This reminds me of “subvocalization” mentioned in a few different sci-fi books.

    Someone make this a product available to the general public so I can buy the crap out of it and use it for some kind of wearable A.I./computer/private phone convo thing.

    • (Score: 2) by patrick on Wednesday August 07 2019, @10:25PM

      by patrick (3990) on Wednesday August 07 2019, @10:25PM (#877239)

      In the 1982 movie, Firefox, Clint Eastwood used this tech to control a Russian built prototype airplane. The catch, he "must think in Russian..." [youtube.com]

    • (Score: 2) by Osamabobama on Wednesday August 07 2019, @10:52PM

      by Osamabobama (5842) on Wednesday August 07 2019, @10:52PM (#877246)

      It made me think of Ender's Game, or maybe the next book in the trilogy. Ender had something similar that he used to communicate with the sentient network lifeform (whom he called Jane) that lived on the ansible links.

      Of course, Ansible is something else now, and I assume the first app to use this subvocalization sensor will be called Jane. Alas...

      --
      Appended to the end of comments you post. Max: 120 chars.
  • (Score: 2) by tangomargarine on Wednesday August 07 2019, @08:16PM (1 child)

    by tangomargarine (667) on Wednesday August 07 2019, @08:16PM (#877209)

    when you’re talking to yourself, even if you’re completely silent and not moving your mouth.

    If you're not making any sound or moving your mouth, how can you call it "talking to yourself"? Isn't that just *thinking*?

    --
    "Is that really true?" "I just spent the last hour telling you to think for yourself! Didn't you hear anything I said?"
    • (Score: 1, Informative) by Anonymous Coward on Wednesday August 07 2019, @08:50PM

      by Anonymous Coward on Wednesday August 07 2019, @08:50PM (#877221)

      It reads signals at the muscles rather than at the brain. They didn't want to make something that read the brain for fear of misuse. So you have to think about talking in addition to thinking about whatever, I think.

  • (Score: 0) by Anonymous Coward on Wednesday August 07 2019, @08:41PM (2 children)

    by Anonymous Coward on Wednesday August 07 2019, @08:41PM (#877214)

    can it hear the voices in my head that arn't me? i'm having a hard time hearing them.

    • (Score: 2) by DannyB on Wednesday August 07 2019, @09:27PM (1 child)

      by DannyB (5839) Subscriber Badge on Wednesday August 07 2019, @09:27PM (#877229) Journal

      The voices told me that I should clean the guns today.

      --
      The server will be down for replacement of vacuum tubes, belts, worn parts and lubrication of gears and bearings.
      • (Score: 0) by Anonymous Coward on Thursday August 08 2019, @02:30AM

        by Anonymous Coward on Thursday August 08 2019, @02:30AM (#877303)

        The voices said MAGA, Make Armament Glitter Again.

  • (Score: 2) by Rupert Pupnick on Wednesday August 07 2019, @08:47PM (3 children)

    by Rupert Pupnick (7277) on Wednesday August 07 2019, @08:47PM (#877219) Journal

    I know a few people for whom such sophisticated neuromuscular processing is not needed.

    • (Score: 0) by Anonymous Coward on Wednesday August 07 2019, @11:40PM

      by Anonymous Coward on Wednesday August 07 2019, @11:40PM (#877258)

      Congress?

    • (Score: 0) by Anonymous Coward on Thursday August 08 2019, @12:21AM (1 child)

      by Anonymous Coward on Thursday August 08 2019, @12:21AM (#877272)

      And I know a few that really need it -- older folks with very faint voice due to age, such that I can barely hear them. Sort of the opposite of hearing aids, these old people need "speaking aids" to be heard and understood.

      This is particularly important in medical settings where the doctor or nurse is asking questions and soon assumes that the old person is suffering from dementia because they aren't answering. The reality is that they are trying to answer, but it's not coming out loud enough (and/or fast enough) to get anyone's attention.

      • (Score: 2) by Rupert Pupnick on Thursday August 08 2019, @03:52PM

        by Rupert Pupnick (7277) on Thursday August 08 2019, @03:52PM (#877517) Journal

        Absolutely— my comment is not a swipe at the idea, rather at some that do have the power of speech.

        I have no idea at all how technically feasible it is. Does this technology already get used in limb prosthetics in simpler form? Any experts out there know the field?

  • (Score: 2) by DannyB on Wednesday August 07 2019, @09:26PM (4 children)

    by DannyB (5839) Subscriber Badge on Wednesday August 07 2019, @09:26PM (#877228) Journal

    If I silently "say" something to someone else, can the system read that? If so, it would seem like the next great:
    1. hardware accessory for smartphones
    2. smartphone app
    For people to silently converse without speaking, typing or gesturing.

    However the other end would have to communicate my thought to the other person. But maybe very quietly through headphones on whatever sensors censors are attached to each person's head.

    --
    The server will be down for replacement of vacuum tubes, belts, worn parts and lubrication of gears and bearings.
    • (Score: 0) by Anonymous Coward on Thursday August 08 2019, @02:06AM (3 children)

      by Anonymous Coward on Thursday August 08 2019, @02:06AM (#877291)

      Two people using the same device with the same A.I. voice... Interesting. Did I say that or did you?

      • (Score: 0) by Anonymous Coward on Thursday August 08 2019, @12:57PM (2 children)

        by Anonymous Coward on Thursday August 08 2019, @12:57PM (#877424)

        You use Microsoft Sam (voice) and I'll use DECTalk -- problem solved!

        • (Score: 2) by DannyB on Thursday August 08 2019, @02:17PM (1 child)

          by DannyB (5839) Subscriber Badge on Thursday August 08 2019, @02:17PM (#877468) Journal

          No, no . . . you want the unique sound of . . .

          THEEEEES EEEEAZE THE TEEE ARE EEHS EIGHTY SPEEEEEECH SYNNNNNTHEEEEESIZZZER.

          --
          The server will be down for replacement of vacuum tubes, belts, worn parts and lubrication of gears and bearings.
          • (Score: 0) by Anonymous Coward on Thursday August 08 2019, @08:01PM

            by Anonymous Coward on Thursday August 08 2019, @08:01PM (#877625)

            Funny, because I wired a speaker to the MB of a TRS-80 so I could hear it. It was like listening to an old 14.4 modem at 1/10th speed.

  • (Score: 4, Informative) by Coward, Anonymous on Wednesday August 07 2019, @10:31PM (7 children)

    by Coward, Anonymous (7017) on Wednesday August 07 2019, @10:31PM (#877242) Journal

    The user hears the A.I.’s responses through a microphone that conducts sound through the bones of the skull and ear...

    Shouldn't it be called a speaker or transducer if it generates sound?

    • (Score: -1, Flamebait) by Anonymous Coward on Thursday August 08 2019, @02:00AM

      by Anonymous Coward on Thursday August 08 2019, @02:00AM (#877290)

      Mr. Arnav Kapur is an indian nigger so finds any language other than hindi challenging.

    • (Score: 2, Disagree) by darkfeline on Thursday August 08 2019, @02:40AM (4 children)

      by darkfeline (1030) on Thursday August 08 2019, @02:40AM (#877309) Homepage

      Microphones and speakers are the same thing. Also, the original use of the word "microphone" referred to an ear trumpet used as a hearing aid

      --
      Join the SDF Public Access UNIX System today!
      • (Score: 0) by Anonymous Coward on Thursday August 08 2019, @02:58AM (1 child)

        by Anonymous Coward on Thursday August 08 2019, @02:58AM (#877318)

        A condenser mic is not a speaker.

        • (Score: 0) by Anonymous Coward on Thursday August 08 2019, @01:00PM

          by Anonymous Coward on Thursday August 08 2019, @01:00PM (#877425)

          > A condenser mic is not a speaker.

          True, but the mechanical/electrical configuration looks a lot like a very small electrostatic loudspeaker.

      • (Score: 3, Informative) by janrinok on Thursday August 08 2019, @07:41AM

        by janrinok (52) Subscriber Badge on Thursday August 08 2019, @07:41AM (#877357) Journal

        Microphones and speakers are the same thing.

        Sometimes that is true, but by no means always.

        --
        [nostyle RIP 06 May 2025]
      • (Score: 2) by DannyB on Thursday August 08 2019, @02:35PM

        by DannyB (5839) Subscriber Badge on Thursday August 08 2019, @02:35PM (#877476) Journal

        A long time ago, in a galaxy far, far away . . .

        there were these microphones called "carbon mics". The diaphragm moved by sound waves compressed carbon powder, altering its resistance to match the sound wave. The neato factor was that one of these could be wired in series with a speaker and 6V battery to talk remotely without any vacuum tubes.

        Long ago, there were telephones that were wired into your home. These phones were big and bulky. Often affixed to a wall. Or on a counter top with a cord that went into a wall plate. (Later plugs were used so that the phone could be unplugged from the wall.) These phones had a handset with a coiled cord. The mic in these handsets was a carbon mic. You could remove the handset from two phones. Wire the mics (mouthpiece) and speakers (earpiece) together in series with a 6V "lantern" battery, and you could talk between the garage and a playhouse in the back yard, needing only two wires going between the two locations.

        --
        The server will be down for replacement of vacuum tubes, belts, worn parts and lubrication of gears and bearings.
    • (Score: 2) by DannyB on Thursday August 08 2019, @02:28PM

      by DannyB (5839) Subscriber Badge on Thursday August 08 2019, @02:28PM (#877471) Journal

      Do microphones produce sound?

      I have not tested this on microphones. But having conducted research [soylentnews.org] in a related field[1][2], I know that LEDs, and diodes that do not emit light, and even resistors can emit sound (as well as light) when provided with sufficient voltage / current. In fact, an ordinary LED touched to the terminals of a 9V rectangular battery emit more sound than light (not measured with test equipment, and units of comparison between sound and light left unspecified).

      [1] [soylentnews.org]
      [2] [soylentnews.org]

      --
      The server will be down for replacement of vacuum tubes, belts, worn parts and lubrication of gears and bearings.
  • (Score: 5, Insightful) by PinkyGigglebrain on Thursday August 08 2019, @12:13AM (4 children)

    by PinkyGigglebrain (4458) on Thursday August 08 2019, @12:13AM (#877269)

    When I think about how this kind of tech could have helped Hawking and others who can't use their own voice to communicate I think "Wow! this is awesome!"

    Then I think about how this will be misused by various organizations/agencies and it isn't that awesome anymore. It become frightening. Consider that when you are asked a question it is your "inner voice" that first responds with the truth, then you decide what you really want to say.

    So what would happen if you forced someone to wear this during an interview or interrogation? Would whoever is looking at the output will know exactly what you REALLY think of the their company or "Glorious Leader"? with the right set of questions you could filter the possible dissidents out of the pool in a very short time.

    I don't know about the rest of you but I would not want anyone to hear most of my internal dialogs.

    --
    "Beware those who would deny you Knowledge, For in their hearts they dream themselves your Master."
    • (Score: 2) by pipedwho on Thursday August 08 2019, @12:35AM (1 child)

      by pipedwho (2032) on Thursday August 08 2019, @12:35AM (#877278)

      Actually, the art of lying to someone else is first by lying to yourself. The sort of dystopian use of this technique that you describe would be even easier to fake out in situations where it actually mattered.

      For example, when asked a question, "are you a Russian spy?"
      Your first pre-programmed and rehearsed thought is, "hell no, I'm a die hard patriot!" ... "for China" ... damn, really that last part was a joke. It just popped into my head. Oh come on bro, please put down the taser. Pleeeeeeezzzzttttttttteeease!!!

      • (Score: 2) by pipedwho on Thursday August 08 2019, @12:42AM

        by pipedwho (2032) on Thursday August 08 2019, @12:42AM (#877280)

        And in the cell across the way:

        PLA: "What is your affiliation with the Tibetan separatists?"
        Tibetan Buddhist monk: "Aum....... Aum........ Aum........"

    • (Score: 2) by DannyB on Thursday August 08 2019, @02:40PM

      by DannyB (5839) Subscriber Badge on Thursday August 08 2019, @02:40PM (#877479) Journal

      It's a good thing that the US would never do anything like that. Only those other bad countries with a Dear Leader.

      --
      The server will be down for replacement of vacuum tubes, belts, worn parts and lubrication of gears and bearings.
    • (Score: 1, Insightful) by Anonymous Coward on Thursday August 08 2019, @03:16PM

      by Anonymous Coward on Thursday August 08 2019, @03:16PM (#877499)

      Exactly my sentiment, this.

      And even worse, imagine these things, with 3g/4g/n+1g uplink, government mandated, doing speech to text and uploading it to be analysed by Department of Public Health and Un-%countryname% Activities!

      They could automate liquidations with drones...

      The upcoming fully managed future just got a bit more horrible.

  • (Score: 0) by Anonymous Coward on Thursday August 08 2019, @01:58AM (1 child)

    by Anonymous Coward on Thursday August 08 2019, @01:58AM (#877289)

    No card memorization needed. Just someone on my team to spot with this technology and me to receive it with this tech too. PROFIT $$$$$

    • (Score: 0) by Anonymous Coward on Thursday August 08 2019, @01:02PM

      by Anonymous Coward on Thursday August 08 2019, @01:02PM (#877427)

      Casinos will figure this out, and you will win a trip to the pokey.

  • (Score: 2) by VLM on Thursday August 08 2019, @01:57PM

    by VLM (445) Subscriber Badge on Thursday August 08 2019, @01:57PM (#877456)

    These limitations could be caused by stroke, cerebral palsy or neurodegenerative diseases like ALS

    For virtue signalling reasons all scientific progress must be intended for certain approved groups, in this case medically handicapped folks.

    In the real world, of course, the first "real" deployed application will be special forces troops who can now talk on their squad radios silently as long as they're not breathing too hard. Should be fairly useful in loud environments also like artillery fire or on the deck of an aircraft carrier.

    So... sure, feel all warm and fuzzy that its all for the poor handicapped people, but you know the first real world deployments are going to be "tip of the spear" military forces, and the Navy Seals are not quite as quaintly correctly left wing pandering.

(1)