Stories
Slash Boxes
Comments

SoylentNews is people

posted by martyb on Wednesday July 31 2019, @05:56PM   Printer-friendly
from the I-heard-what-you-were-thinking-of-saying dept.

Team IDs Spoken Words and Phrases in Real Time from Brain's Speech Signals

UC San Francisco scientists recently showed that brain activity recorded as research participants spoke could be used to create remarkably realistic synthetic versions of that speech, suggesting hope that one day such brain recordings could be used to restore voices to people who have lost the ability to speak. However, it took the researchers weeks or months to translate brain activity into speech, a far cry from the instant results that would be needed for such a technology to be clinically useful. Now, in a complementary new study, again working with volunteer study subjects, the scientists have for the first time decoded spoken words and phrases in real time from the brain signals that control speech, aided by a novel approach that involves identifying the context in which participants were speaking.

[...] In the new study, published July 30 in Nature Communications [DOI: 10.1038/s41467-019-10994-4], researchers from the Chang lab led by postdoctoral researcher David Moses, PhD, worked with three such research volunteers to develop a way to instantly identify the volunteers' spoken responses to a set of standard questions based solely on their brain activity, representing a first for the field.

To achieve this result, Moses and colleagues developed a set of machine learning algorithms equipped with refined phonological speech models, which were capable of learning to decode specific speech sounds from participants' brain activity. Brain data was recorded while volunteers listened to a set of nine simple questions (e.g. "How is your room currently?", "From 0 to 10, how comfortable are you?", or "When do you want me to check back on you?") and responded out loud with one of 24 answer choices. After some training, the machine learning algorithms learned to detect when participants were hearing a new question or beginning to respond, and to identify which of the two dozen standard responses the participant was giving with up to 61 percent accuracy as soon as they had finished speaking.

[...] Moses's new study was funded by through a multi-institution sponsored academic research agreement with Facebook Reality Labs (FRL), a research division within Facebook focused on developing augmented- and virtual-reality technologies. As FRL has described, the goal for their collaboration with the Chang lab, called Project Steno, is to assess the feasibility of developing a non-invasive, wearable BCI device that could allow people to type by imagining themselves talking.

See also: Facebook gets closer to letting you type with your mind
Brain-computer interfaces are developing faster than the policy debate around them

Previously: Brain Implant Translates Thoughts Into Synthesized Speech


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.
  • (Score: 1) by jmichaelhudsondotnet on Thursday August 01 2019, @11:43AM

    by jmichaelhudsondotnet (8122) on Thursday August 01 2019, @11:43AM (#873961) Journal

    Wittgenstein said don't make any statements that you are not absolutely certain about.

    I am certain facegag from its inception has been integrated with Darpa due to that project that was cancelled on the same day, also Zuckerborg is not capable in any way of preventing basically his entire board of directors from being actual trained spies, nor any of his sys admin team. And then there's that bizarro pentagram cult they have going on indicated by the inside of his hoodie which he only accidentally revealed.

    It is clear to me that something is going on that steamrolls over the definition of business and government and we are using words that only barely match up with what we are talking about.

    I think maybe what we should be more alarmed about is that there are no journalisetic entities remaining who would even try to answer these questions, we're all looking up at these institutions like loincloth wearing exiles in a Dali painting and the most we can say for certain is that they are excercising power and being extremely secretive about their intentions while literally moutains of propaganda and degenerate asocial media entities rain down.

    Have you thought recently about how small listening devices might be with nano tech? Do you really think if exxon didn't reveal what it knew about climate disaster in 1972 that versizombie is going to reveal the true capabilities and risks of 5G?

    You should be scared about how little we know and how virtually every institution from a structural functional perspective is inherently designed to deceive, and that there seem to be no remaining entities capable of even explaining to us what our rights are or what technologies are being used to negate them.

    We think technocracy means rule by gorgle admins, but it could also mean whoever gets their first can simply impose an -ocracy with their new gadget.

    At least I can say that no one should be developing mind control tech without strict oversight, same should be said for AI, viruses, things that go boom and anything else that will be impossible to isolate if it escapes from the lab.

    In order to defend america, not only does america have to be first to get the tech, but the citizens have to be told about it at that time, otherwise their rights are inherently violated. This is of course the reasining for wearing a tinfoil hat, if they can read your mind from space and transmit adverts to your sleeping brain, your faraday cage waterbed is a rational idea and not using one is insane.

    Of course, when your neighbors start marching down the street in lockstep with glazed eyeballs and surround your house chanting, it will be too late.