Speech synthesis has been an integral, if sometimes maligned, part of interactive voice response, or IVR, for years. The maligning has dissipated recently as IVR has begun employing more advanced, natural-sounding speech synthesis tools.
But IVR isn’t the only driver of speech synthesis advancement. A new film sketch by “Britain’s only stand-up comedian to use a solely computer-generated voice” illustrates how speech synthesis can help individuals who have lost their ability to speak.
According to the BBC, Lee Ridley’s sketch—Voice by Choice—takes us to a speed-dating event with three people who rely on speech synthesis to talk, showing us some of life with computerized speech.
“I don’t need to rely on other people to get my message across anymore,” Ridley told the BBC. “It has made me a lot more independent and a lot more confident.”
While there’s apparently some awkwardness, the technology enables a freedom Ridley and others couldn’t have otherwise.
“I felt dead,” Voice by Choice actress Nicola Bush told the BBC. “But when I got my first voice [at age 15], it opened important doors for me.”
Ridley and Bush aren’t the only ones. American film critic Roger Ebert uses a custom speech synthesis tool to create speech that mimics his own (to a degree). Having his own voice helps Ebert impart emotion and personality into his speech a little better.
For Ebert, Scottish speech synthesis research company CereProc used digital recordings of Ebert’s own voice (there were lots of them) to create his voice application, according to CBS News.
“Voice clones are a natural progression of our technology,” CereProc’s Matthew Aylett told TechNewsDaily.
The implications for healthcare are obvious.
“Someone who is about to lose their voice for medical reasons can record their speech in advance,” Alan Black of Carnegie Mellon University’s Language Technologies Institute told CBS News.
While that didn’t work for Ebert, who the BBC says lost his voice suddenly, it could work for many other people. Especially if/when their healthcare professionals are aware of the latest available speech synthesis technologies.