Neural interface can help complete paralyzed person speak at 62 words per minute
A voice neural interface decoded speech at 62 words per minute, which is 3.4 times quicker than the previous analogue record.
The error rate using a vocabulary of 125,000 words was 23.8%, meaning that not every word was recognized by the decoder.
The voice neural interface assisted a paralyzed patient who cannot talk due to sickness in pronouncing words, bringing us one step closer to a world without communication barriers between patients who cannot communicate and the outside world.
The interface links to the brain and decodes cerebral activity, which is brought on by attempts to speak before converting it to text and then using the standard text-to-speech procedure to produce sound. In conclusion, this neural interface decoded speech at a pace of 62 words per minute, which is 3.4 times quicker than the previous analog record.
|Related article: Arab Health explores healthcare in the metaverse, predicts the industry value of $5.37 billion by 2030|
Although the results of these initial testing of this interface are encouraging, researchers have not yet attained high accuracy for transferring texts from a broad vocabulary. The error rate using a vocabulary of 125,000 words was 23.8%, meaning that not every word was recognized by the decoder. The rate is rather high at the moment, but you can bet that understanding 70% of a person who is entirely paralyzed said, which is quite cool in and of itself.
Read more related news:
Any data, text, or other content on this page is provided as general market information and not as investment advice. Past performance is not necessarily an indicator of future results.
The Trust Project is a worldwide group of news organizations working to establish transparency standards.