Generation of Synthetic Speech Through Brain Recordings

Our ability to speak is one of God’s greatest blessing to us. Stroke, traumatic brain injury, and neurodegenerative diseases for example Parkinson's disease, multiple sclerosis, and amyotrophic lateral sclerosis (ALS, or Lou Gehrig's disease) usually cause an irreversible loss of the ability to speak.  Some people suffering with extremely severe disabilities usually learn the art of spelling out their thoughts letter by letter with the help of assistive devices that track extremely small eye or facial muscle movements.

These assistive devices are very common these days but these are not very efficient. The task of producing text or synthesized speech with the help of these devices is a very laborious, error-prone, and painfully slow task, typically permitting a maximum of 10 words per minute, compared to the 100-150 words per minute of natural speech. The new system that is under development in the laboratory of Edward Chang, MD -- described April 24, 2019 in Nature -- shows that it is possible to create a synthesized mode of a person's voice. Such a voice is controlled by the activities of their brain's speech centers. In the future, this approach shall not only provide fluent communication to the individuals with severe speech disability, but shall also create some of the musicality of the human voice that conveys the speaker's emotions and personality beautifully. The study is depictive of the fact that entire spoken sentences can be generated based on an individual's brain activity. This is an exhilarating proof of principle that with the technology that is already within reach, we should be able to build a device that is clinically viable in patients suffering from speech loss. The research was carried out by Gopala Anumanchipalli, PhD, a speech scientist, along with Josh Chartier, who is a bioengineering graduate student in the Chang lab. It is based on a recent study wherein the pair described for the very first time that how the human brain's speech centers perform the movements of the lips, jaw, tongue, and other vocal tract components in order to produce fluent speech.

By:  Anuja Arora

Content: https://www.sciencedaily.com/releases/2019/04/190424153558.htm