A way to “Detect Speech” from People’s brain

We don’t just make any old ran­dom noise when we talk; we’re think­ing about our words, and that makes us able to speak fluently.

Meta’s new AI can scan a person’s brain­waves to “hear” what some­one else is say­ing to them. In oth­er words, it can tell which words you hear by read­ing your brain­waves. This is not the first time this con­cept has got­ten spot­light. In 2019, Amer­i­can sci­en­tists had devel­oped an arti­fi­cial intel­li­gence that could accu­rate­ly read brain sig­nals and trans­late them into speech.

Talk­ing about the Meta’s recent AI, it can decode speech from non­in­va­sive record­ings of brain activ­i­ty. Neu­ro­sci­en­tists have always dreamt of decod­ing speech from some­one’s brain for a long time, but inva­sive meth­ods were need­ed to achieve this.

The spe­cial­ty of the new tech­nique, accord­ing to the researchers, is that it is non-inva­sive, which means that researchers do not have to implant like… elec­trodes, in anyone’s brain.

Non­in­va­sive tech­niques such as elec­troen­cephalo­grams, EEG, and mag­ne­toen­cephalog­ra­phy, MEG, can scan the brain from the out­side and watch activ­i­ty with­out any surgery, but the prob­lem is that they are too noisy.

In order to address this prob­lem, researchers turned to machine learn­ing algo­rithms to help “clean up” the noise. They used the mod­el wave2vec 2.0.

Brain-wave-read­ing AIs seem to be an excit­ing new tech­nol­o­gy that can be used to help peo­ple with speech prob­lems, like peo­ple who can’t speak, and those who have had strokes or oth­er issues that cause speech difficulties.

But so far, only lab-based research has been done on brain­wave-read­ing AI. They haven’t been avail­able for use in the real world yet.

The future of Neural AI technologies 

The future of AIs is will not be lim­it­ed to be act­ing as a cure for peo­ple with speech prob­lems. With advance­ments in tech­nol­o­gy, it’s not far­fetched to think that advanced form of AI could be used as ways for com­put­ers to com­mu­ni­cate with each other. 



As seen by sci­en­tists and AI researchers, brain com­mu­ni­ca­tion will help humans work bet­ter togeth­er with arti­fi­cial intel­li­gence and machines. The day is com­ing, some say it has already.

Potential Misuses?

When we think about the future of tech­nolo­gies like Meta’s Brain-wave-read­ing AIs, we should­n’t for­get about the poten­tial for mis­use, should we?

In the future, will these kinds of hacks also be pos­si­ble against our brains? Could crim­i­nals hack into our minds to get infor­ma­tion from us?

Well, we do have trou­ble with peo­ple who spread false news sto­ries on social media to stir up anger. But still, that’s too much for assumption.

In fact, it’s too child­ish to stop the progress of some­thing new just because it has some poten­tial for mis­use. Let’s keep in mind that peo­ple can also use every sin­gle piece of tech­nol­o­gy for evil pur­pos­es, and they still do it.

Meta’s new steps are look­ing promis­ing, and we are in the cor­rect path among few, at least, till now.

Leave a Reply

Your email address will not be published.

Join our NewsletterDaily Glimple of Future

Our blog, "Daily Glimpse of Future", strives to make the future much clearer than it is today. Join our newsletter for free now.