Scientists Created An Algorithm That Converts Thoughts Into Speech

Honestly now, how many times have you thought of being able to listen to someone’s thoughts? Heard about turning thoughts into speech? It’s possible. 

I know I personally would love to have a superpower like this. Especially after watching those endless fantasy movies that appeal to human imagination. 

So now, how would you feel if I told you this might be a possible thing? Yes, this is no longer limited to movies and you can welcome this ‘superpower’ soon in your life.

What, I’m serious! You don’t believe me? Well okay, then please allow me a chance to win your trust in this.

Turning Thoughts Into Speech

Scientists were able to produce clear and understandable speech through by processing human brain activity.

This amazing breakthrough was achieved by the researchers of the Zuckerman Institute at the University of Columbia. They were able to reconstruct the words a person heard by monitoring their brain activity.

Scientists have used similar technology as found in smart assistants like Amazon’s Alexa and Apple’s Siri – the Vocoder.

Using the technology of vocoder?

A vocoder is a computer algorithm that can produce human speech through analysis of speech input. So how did the scientists make use of a vocoder to translate human thoughts into speech?

Scientists taught such a vocoder to recognize and translate brainwave patterns into human speech. 

Scientists call it Brain Computer Interface (BCI)

What does that even mean? Don’t worry, we’ll tell you. A BCI is a bidirectional communication route between a brain and a computer. In short, it both sends and receives signals.

About the research 

The research team was lead by Doctor Nima Mesagarni, who partnered with neurosurgeon Ashesh Dinesh Mehta of Northwell Health Physician Partners Neuroscience Institute.

Researchers measured the brain activity of some epilepsy patients who were already undergoing brain surgery. 

They measured the neural activity of five study participants while they listened to four speakers present short stories for half an hour. These recorded neural patterns were then used to train the vocoder to synthesize a human voice.

“Working with Doctor Mehta, we asked epilepsy patients already undergoing brain surgery to listen to sentences spoken by different people, while we measured patterns of brain activity. These neural patterns trained the vocoder,” said Professor Mesgarani.

Researchers view their brain-to-computer systems as state of the art and a step towards the next generation of human-computer interaction systems and more natural communication channels for patients suffering from paralysis and locked-in syndromes.

“This would be a game-changer”

This is not an actual voice, yes. This won’t give them back their original voice, yes. Many still might argue that it’s not smart to let AI take such control over our lives, yes. But…

Can you imagine not being able to communicate for one day? Just think of waking up a random day and being voiceless. Or losing it after an accident or some illness.

This technology, despite all the protests against the AI revolution, is a blessing to those who are not gifted with something as basic as a voice.

Professor Mesgarani said, “This would be a game-changer. It would give anyone who has lost their ability to speak, whether through injury or disease, the renewed chance to connect to the world around them.”

And what happens to privacy?

Well, that remains one concern, doesn’t it? What our researchers envision is a device that will only translate the thoughts on command. 

But does it not leave possibilities of a security breach, like most devices today? It can surely become a doorway to hacking the human thoughts. Now that is another topic for discussion. 

Until you decide the moral implications of this new technology, take care of friends! Goodbye!