Friday, December 30, 2011

OPINION - The man who saves Stephen Hawking's voice

The man who saves Stephen Hawking's voice

Sam Blackburn has been responsible for the technology which allows Stephen Hawking to communicate for the past five years. Now he's moving on. The challenge for his successor: to keep that well-known voice in working order

You have been Stephen Hawking's technician since 2006. What was top of your to-do list when you started work?
At first the system was breaking all the time. I'd get calls at 1 o'clock in the morning saying "Stephen can't speak, what do we do?" So I needed to modernise the system. One of the first pieces I improved was the infrared sensor mounted on Stephen's cheek. That kind of incremental improvement is much easier for him to accept than a radical new system, because the learning curve associated with that is very steep. Stephen wouldn't be able to ask for help because the very thing he wouldn't be able to use would be the speech system. Understandably that has made him very reluctant to upgrade.

Stephen's voice is very distinctive, but you say there might be a problem retaining it?
I guess the most interesting thing in my office is a little grey box, which contains the only copy we have of Stephen's hardware voice synthesiser. The card inside dates back to the 1980s and this particular one contains Stephen's voice. There's a processor on it which has a unique program that turns text into speech that sounds like Stephen's, and we have only two of these cards. The company that made them went bankrupt and nobody knows how it works any more. I am trying to reverse engineer it, which is quite tricky.

Can't you update it with a new synthesiser?
No. It has to sound exactly the same. The voice is one of the unique things that defines Stephen in my opinion. He could easily change to a voice that was clearer, perhaps more soothing to listen to – less robotic sounding – but it wouldn't be Stephen's voice any more.

How exactly does Stephen communicate?
He has used a menu controlled by a computer system to speak since about 1986. Basically, a computer highlights cells in a big grid of letters or words, and when the correct one is highlighted the user presses a switch of some sort. When he became unable to move his hands sufficiently to use the switch, he moved to an infrared system mounted on his glasses, which detects movement in his cheek muscle.

What's going to happen when Stephen can no longer use the muscles in his cheek?
Stephen has motor neurone disease, which causes a progressive decay of the nerves, and now his facial muscles are the only ones he can control reasonably well. Those are now fading too, unfortunately. This has always been known, but Stephen has outlived all the estimates for the stages of his nerve decay.
The result is that the system has now become very slow. Stephen's rate of speech is down to about one word per minute, and while I am making slight advances in the technology he is using, the nerve decay has now reached the point where we need to move to some new technology. We have tried some eye-tracking systems; the other method is brain scanning, and there are all sorts of techniques for that. So far we have only considered those that don't require intervention – no surgery certainly, and no shaving of the head.

Is he excited about the prospect of using such cutting-edge technologies to communicate better?
I find it exciting. Stephen has a stubborn attitude towards this sort of thing. He feels that he has to prove he can still use his existing system. The result is that when there is a communications expert in the room – someone trying to show him new technology – his speed using the existing system suddenly increases.

No comments:

Post a Comment