People who are not able to talk due to some medical condition or loose voice due to some accident may able to gain their view. The new technology can turn the brain activity into speech, according to the scientists of California University. The scientists have decoded the cerebral speech by implanting electrodes into the volunteer’s brain. The process helps to generate the statement by the help of a synthesizer. The vocal tract of the individual such as tongue, jaw, larynx, and lips becomes computer stimulated by this process that leads to the generation of voice.
The researchers of California University at San Francisco are hopefully about the invention. The technology can be incorporated into a device with further research. A clinically improved device can be created by using this technology to help people who lose their voice. The study was published on Wednesday. According to Josh Chartier- a doctoral student and the co-author of the study, the discovery is shocking and the intelligible. The output of the synthesizer provides several aspects of the natural voice which is incredible. The study has given much production that can be studied further to get a more vivid idea about the process.
The device which was used by many people tracks only facial muscle and eye movements to spell the words out. The words synthesized by these devices are slow and letter by letter. The machine produces about ten words per minute while naturally humans speak up to 100-150 words in a minute. Various medical conditions take away the ability to talk in humans. The terms are such as amyotrophic lateral sclerosis, cerebral palsy, multiple sclerosis, and Parkinson’s disease. Some severe brain injury, cancer, and paralysis can also be responsible for voice loss in humans.
The current study has involved patients with epilepsy, and they can speak. The individuals will be treated with electrodes for their neurosurgery, so they were the volunteers of the study. An artificial vocal track was created for each volunteer that can track the brain activity. The volunteers are made to read out in a loud voice so that the brain activity which is responsible for language production can be tracked. The synthesizer follows the synthesized speeches that are produced by the brain activity of the volunteers.
According to Edward Chang- the senior author of the concerned study, the research is the attempt to decode the movements of the vocal tract as brain activity is involved in the translation of the thoughts. The action by the brain is expressed through the vocal tract. The new technology can track speeches such as “sh” whereas the technology doesn’t work to follow some other sounds- “p” and “b.” The brain activity can’t be decoded without the incorporation of the vocal track, which is virtual in nature. The researchers said, they will next study the same technology in people who are not able to speak. So, they can discover some new facts about the technology for future application.