In Scientific Reports, neuro-engineers developed a system that translates thought into intelligible and recognizable speech through detections of brain activity that ultimately reconstruct the words a person hears with unprecedented clarity. The system can help people who cannot speak, those living with amyotrophic lateral sclerosis (ALS), or individuals recovering from stroke.
"Our voices help connect us to our friends, family and the world around us, which is why losing the power of one's voice due to injury or disease is so devastating," says Nima Mesgarani, PhD, the paper's senior author and a principal investigator at Columbia University's Mortimer B. Zuckerman Mind Brain Behavior Institute. "With today's study, we have a potential way to restore that power. We've shown that, with the right technology, these people's thoughts could be decoded and understood by any listener."
Previous research has confirmed that when someone speaks or even thinking of saying something—patterns of brain activity begin to surface. Early efforts of the study focused on decoding brain signals through the utilization of computer models that analyzed spectrograms (the visual representations of sound frequencies). However, this approach has failed and so the study shifted to the use of a ‘vocoder’ which is a computer algorithm capable of synthesizing speech after being trained on voice recordings of human conversations
"This is the same technology used by Amazon Echo and Apple Siri to give verbal responses to our questions," said Dr. Mesgarani, who is also an associate professor of electrical engineering at Columbia's Fu Foundation School of Engineering and Applied Science. "Working with Dr. Ashesh Dinesh Mehta (co-author of the study), we asked epilepsy patients already undergoing brain surgery to listen to sentences spoken by different people, while we measured patterns of brain activity," said Dr. Mesgarani. "These neural patterns trained the vocoder."