Roger Ebert, the most well-known film reviewer in the US, lost the ability to speak four years ago after life-saving cancer surgery.
However, computer technology developed by Cereproc, a company spun out of Aberdeen University, has been able to reconstruct Ebert’s original voice by using recordings of television appearances and DVD commentaries.
To reconstruct Ebert’s voice, the company - formed in 2005 - mined the recordings to create a comprehensive database of words and sounds. As a result, when Ebert speaks, listeners who heard him in the past will still recognise his voice today.
Ebert - who is famous for his thumbs-up or thumbs-down film reviews, and is the only film critic ever to win a Pulitzer prize for journalism - can now communicate, using a laptop, by typing sentences that are converted by a synthesiser into the sound of his own voice.
In a televised interview with Oprah Winfrey, Ebert demonstrated the technology by predicting this year’s Oscar-winning films.
Unlike the types of speech systems developed in the 1980s - such as that used by Prof Stephen Hawking - Cereproc’s synthesised voices have character and emotion.
’We specialise in producing voices that have got a bit of character and don’t sound neutral or boring. This synthesis sounds very much like a natural voice,’ said Cereproc’s chief technical officer Dr Matthew Aylett.
Oxa launches autonomous Ford E-Transit for van and minibus modes
I'd like to know where these are operating in the UK. The report is notably light on this. I wonder why?