![\"Masahiro](\"\/\/media.nature.com\/w800\/magazine-assets\/d41586-019-01328-x\/d41586-019-01328-x_16672812.jpg\")
<\/div>\n<\/div>People with paralysing conditions such as motor-neuron disease often rely on technology to help them speak.<\/span>Credit: BJ Warnick\/Alamy<\/p>\n<\/figcaption><\/figure>\n <\/p>\n <\/p>\n In an effort to provide a voice for people who can\u2019t speak, neuroscientists have designed a device that can transform brain signals into speech.<\/p>\n This technology isn\u2019t yet accurate enough for use outside the lab, although it can synthesize whole sentences that are mostly intelligible. Its creators described their speech-decoding device in a study1<\/a><\/sup>published on 24 April in\u00a0Nature<\/i>.<\/p>\n Scientists have previously used artificial intelligence to translate single words2<\/a><\/sup>,<\/sup>3<\/a><\/sup>, mostly consisting of one syllable, from brain activity, says Chethan Pandarinath, a neuroengineer at Emory University in Atlanta, Georgia, who co-wrote a\u00a0commentary<\/a>\u00a0accompanying the study. \u201cMaking the leap from single syllables to sentences is technically quite challenging and is one of the things that makes the current work so impressive,\u201d he says.<\/p>\n <\/p>\n Mapping movements<\/strong><\/p>\n Many people who have lost the ability to speak communicate using technology that requires them to make tiny movements to control a cursor that selects letters or words on a screen. UK physicist Stephen Hawking, who had motor-neuron disease, was one famous example. He used a speech-generating device activated by a muscle in his cheek, says study leader Edward Chang, a neurosurgeon at the University of California, San Francisco.<\/p>\n Because people who use such devices must type out words letter by letter, these devices can be very slow, producing up to ten words per minute, Chang says. Natural spoken speech averages 150 words per minute. \u201cIt\u2019s the efficiency of the vocal tract that allows us to do that,\u201d he says. And so Chang and his team decided to model the vocal system when constructing their decoder.<\/p>\n <\/p>\n Researchers implanted electrodes similar to these in participants\u2019 skulls to record their brain signals.<\/span>Credit: UCSF<\/p>\n<\/figcaption><\/figure>\n <\/p>\n <\/p>\n The researchers worked with five people who had electrodes implanted on the surface of their brains as part of epilepsy treatment. First, the team recorded brain activity as the participants read hundreds of sentences aloud. Then, Chang and his colleagues combined these recordings with data from previous experiments that determined how movements of the tongue, lips, jaw and larynx created sound.<\/p>\n The team trained a deep-learning algorithm on these data, and then incorporated the program into their decoder. The device transforms brain signals into estimated movements of the vocal tract, and turns these movements into synthetic speech. People who listened to 101 synthesized sentences could understand 70% of the words on average, Chang says.<\/p>\n <\/p>\n <\/p>\n![\"A](\"\/\/media.nature.com\/w800\/magazine-assets\/d41586-019-01328-x\/d41586-019-01328-x_16672810.jpg\")
<\/div>\n<\/div>