Artificial Intelligence (AI) is becoming more and more useful to people with time. Cambridge scientists have created a wearable device. This wearable collar powered by Artificial Intelligence (AI) will help stroke patients to speak with their own voice again. The AI collar, ‘ReVoice’, understands the wearer’s speech cues and emotions. It creates complete sentences from pieces of spoken words. The device is vastly superior to existing speech assistance technologies, which are either not successful or require brain implants. Let us know about it in detail.
Great need for portable speech solution
Professor Luigi Occhipinti, from the Department of Engineering at the University of Cambridge, who led the research, said that stroke patients are often able to speak sentences after a lot of practice, but they have difficulty in everyday conversation. He also said that many patients eventually regain most or all of their voice, so brain implants are not necessary. However, there is a strong need for speech solutions that are easier to use and more portable.
How does this device work?
The ReVoice wearable device gives stroke victims the ability to speak independently in their own voice without the need for a brain implant. A trial was conducted on five patients. These patients had dysarthria, a common speech problem that occurs after stroke. The ReVoice device reduced mistakes in sentences by 2.9%. The device captures slight vibrations from the wearer’s neck through sensors. It also infers the emotional state of the wearer from the pulse signal.
This device is equipped with LLM model
It includes a Large Language Model (LLM), the same AI technology used in popular chatbots like ChatGPT. It helps in guessing complete sentences. It is hoped that this technology can also be used for people suffering from other neurological problems like Parkinson’s and motor neurone disease.
There is a great need for clinical trials
Professor Occhipinti explained that when people have dysarthria after a stroke, it can be very frustrating for them. They know what they want to say, but physically can’t speak because the stroke has disrupted the signals between their brain and throat. The researchers aim to develop a multilingual device in the future that can understand emotions. However, clinical trials will be required before it can be made available on a large scale.
Will also be useful for other neurological diseases
This research has been published in a popular journal like Nature Communications, which shows that this is a serious and important study. This may have even bigger consequences in the future. This technology will not be limited only to stroke patients, but it can also become a ray of hope for people suffering from other neurological diseases.