Scientists have created an algorithm that converts thoughts into speech. He can deal with full sentences

Atom2Vec-artificial-intelligence

What would have been considered a miracle a few decades ago is now possible thanks to the development of science. In this case (nomen omen) we are talking about direct exchange of thoughts into speech.

The prototype of the speech to speech device arose at the University of California in San Francisco, and although it can process whole sentences, it is not yet accurate enough to be used outside the laboratory. At least for now.

Turning thoughts into speech possible thanks to artificial intelligence

Scientists have previously used artificial intelligence to translate individual words, usually monosyllabic, based on the analysis of brain activity. However, compared to the processing of full, polysyllable sentences, these initial experiments could be described as primitive. Therefore, it is only in this case that we can talk about any breakthrough resulting from the research of scientists from the University of California in San Francisco led by Dr. Edward Chang.

Let's start from the beginning. To be able to count on any chance of success of such a demanding project, you had to find the right volunteers first. The Chang team invited five patients to participate in their experiment, who were implanted with electrodes on the surface of the brain as part of epilepsy treatment. In addition to therapeutic options, the electrodes placed in this way allow for accurate monitoring and recording of participants brain activity. It was a key condition.

With this combination , patients were asked to read several hundred sentences aloud. During the reading, the Chang team focused on the analysis of brain activity responsible for controlling the speech engine.

Here you should do a brief digression about the fact that the movements performed by our voice apparatus (mouths, voice pages, air exhale, etc.) are controlled directly from the brain. This means that by reading the exact signal from the electrodes implanted in the patients, scientists were able to obtain a pattern by which the given word is spoken out loud.

After building a sufficiently large database, the researchers proceeded to the final stage of the experiment. Patients were asked to ... think about saying the same sentences without saying them out loud.

You can listen to the effects

https://www.youtube.com/watch?v=kbX9FLJ6WKw

The method will not work in every case

I'm not saying, of course, that the algorithm developed by Dr. Chang, by his limitations, is completely useless. Certainly, not everyone will be able to communicate with him without moving his mouth. Remember that the decoder's operating principle requires the user to have a fully trained voice apparatus. The same trick, in the case of a person who was never able to speak alone will not work - her brain has no idea how to control the vocal apparatus, so that he can form words and complete sentences with it.

This does not mean, however, that the device is useless. Many people who have lost the ability to speak will certainly benefit from it. Current cameras that allow them to communicate require them to make small movements that control the cursor, which selects letters or words on the screen. A famous example was the British physicist Stephen Hawking , who used the device to generate speech activated by the cheek muscles.

Communicating in this way has its serious limitations. For example, because of the speed of such synthetic speech. Currently offered cameras allow you to say about ten words per minute. In comparison to our natural pace, that is say 150 words per minute. it is not too much.

Do not forget about commercial use. Just think about office implants, thanks to which writing on the keyboard would be completely unnecessary. Already now, several people in our editorial office sometimes write texts, dictating them to their smartphone or computer. This solution would probably not work in a stationary editorial, so such an implant would make the most sense.



Scientists have created an algorithm that converts thoughts into speech. He can deal with full sentences

Comments

Popular posts from this blog

What is VoLTE and how can you activate it on your Xiaomi

So you can check the battery status of your Xiaomi smartphone and how many cycles you have performed

How to exit the FASTBOOT mode of your Xiaomi if you have entered accidentally

Does your Xiaomi charge slowly or intermittently? So you can fix it

Problems with Android Auto and your Xiaomi? So you can fix it

If your Xiaomi disconnects only from the WiFi it may be because of that MIUI setting

How to change the font in MIUI and thus further customize your Xiaomi: so you can change the type, color and size of the letters of MIUI

What is the Safe Mode of your Xiaomi, what is it for and how can you activate it

Improve and amplify the volume of your Xiaomi and / or headphones with these simple adjustments

How to activate the second space if your Xiaomi does not have this option