We are excited to let you know that SwiftKey has been part of an ambitious project to enhance the communication system used by world-renowned scientist Professor Stephen Hawking.
For the past two years, the SwiftKey team has collaborated with the bestselling author and Intel to make it easier for him to write and communicate. Today SwiftKey joined Intel and Professor Hawking on stage in London to talk about this work.
Professor Hawking has motor neurone disease and as such is only able to communicate by using a small sensor which is activated by a muscle in his cheek. He uses this sensor to ‘type’ characters and numbers on his keyboard. SwiftKey’s technology has been integrated into his current system so that it can accurately predict whole words, rather than just characters. That means that the time and effort Professor Hawking requires to type is significantly reduced, allowing for a much easier, speedier experience for him.
SwiftKey built a personal “language model” for Professor Hawking based on his extensive works – including documents not published in the public domain. The software learns from him to ensure it predicts contextually relevant words. It is also able to analyze the content of the specific book or lecture that he might be working on, further tailoring its predictions and autocorrections.
We found that the nature of Professor Hawking’s mistakes is fundamentally different to those mistakes of your average smartphone user. While one of our biggest demographics is the fast, sloppy typist who writes texts or tweets, Professor Hawking is an excellent, accurate speller and uses his system to write long-form lectures and books. The aim was to enable him to write and speak with greater ease for longer periods and minimise typos.
Joe Osborne, SwiftKey’s SDK team lead, who led our work on this project, said: “It has been a wonderful experience to work so closely with Professor Hawking and his team on this project, integrating our technology into his communications system. SwiftKey’s predictive technology learns from each individual user, gaining insights from their personal language style.
“We built a bespoke version for Stephen, adapting it to suit the particular challenges he faces, whether he is giving lectures, writing chapters of a new book or engaging in conversation. We estimate that our technology has roughly doubled Professor Hawking’s speech rate to date. By understanding the way he uses language, SwiftKey’s technology makes it faster and easier for Stephen to communicate, leaving him more time to consider the secrets of the universe,” he added.
At SwiftKey we feel privileged to have played a role in improving the communications of one of our greatest living scientists. As a team it makes us incredibly proud that our technology is being used to enhance communication in its broadest sense, and we believe that our work with Intel and Professor Hawking and his team will provide insights that are able to shape and improve our work in the future.
If you are interested in learning more about Professor Hawking’s work, you can discover more on his website. If you would like to know more about other examples of adaptive technology powered by SwiftKey, check out our work with pioneering Israeli startup Click2Speak.
Sarah Rowley and the SwiftKey Team