A crew of researchers at the University of California, San Francisco, has taken another step towards the development of a computer able to decipher speech in the human mind. In their paper featured in the journal Nature Neuroscience, the group defines their approach to utilizing AI systems to learn and translate human thoughts. Gregory Cogan, with Duke University, has revealed a News & Views piece outlining the work by the crew in California in the identical journal difficulty.
Over the previous century, people have puzzled if it might be possible to create a machine that could learn the human mind. Such concepts have most often been expressed in films where scientists attempt to read the thoughts of a spy or terrorist. Not too long ago, such techniques have come to be seen as a potential way for people with a speech disability to speak. The advent of artificial intelligence (AI), and more specifically neural networks, has brought the possibility ever closer, with machines capable of reading mind waves and translate some of them into phrases. In this new effort, the research team has taken the idea a step ahead by creating a system capable of deciphering entire sentences.
The work by the group involved creating a more advanced AI system and recruiting the help of four women with epilepsy—each of whom had been fitted with brain-implanted electrodes to monitor their condition. The researchers used readings from the electrodes to capture mind signals in several parts of their brain as the women read sentences out loud.