Neurologists at Columbia University in New York have developed a system that translates thought into intelligible words, shifting brain sign to words for the first time.
This technology, based on voice synths and artificial intelligence, reconstructs the words that a person listens with unmatched clarity.
According to Nima Mesgarani and his colleagues, this discovery marks a decisive step towards the creation of brain-computer interfaces that allow expressing people with limited or non-existent disability, especially those who live with stroke sequelae or with amyotrophic lateral sclerosis or ELA, one nervous system disease that attacks nervous cells (neurons) and spinal cord
In addition, according to the researchers, this development could lead to new forms of communication between computers and the human brain.
"Our voice helps us to communicate with our friends, our family and the world that surrounds us, therefore losing their use as a result of an injury or illness is terrible," said Nima Mesgarani. He adds: "our study represents a way to restore this power. We show that with the right technology, any listener can decipher and understand the thoughts of a person."
Brain patterns of words
In the last decades, the work of the neuroscientists has shown that certain particular patterns of activity appear in the brain when a person expresses themselves with the word (or imagine what he does). Other particular signs also appear in the brain when a person listens to another.
These two observations led investigators to record and decode these patterns or neuronal code in order to perceive the thoughts that circulate in the brain and translate them into words.
The previous efforts of this team, but also from other research groups, focused on simple computer models that analyze spectrograms, which are visual representations of sound frequencies. But this vision was not successful, since it could not reproduce intelligible sounds similar to those of speech.
As a result of this failure, Nima Mesgarani's team abandoned the spectrogram and became a vocoder, a computer algorithm that can synthesize the speech after being trained to listen to human conversations.