Recently, Esquire published an exquisite cover story on film critic Roger Ebert, who is best known for the decades he spent debating great and not-so-great films with his counterpart Gene Siskel on the popular television programme, viagra 50mg At the Movies. Since the article came out last month, people can’t get enough of Ebert. His blog, which was already popular, has developed cult popularity, he has well over 100,000 followers on Twitter, he’s recently created a Fan Club (inspired by an old friend who also happens to be a successful web porn entrepreneur) and he was a guest on Oprah.
Although there are hundreds of hours of footage of Ebert’s voice in At the Movies, it seemed very unlikely, if not impossible, that he would ever be able to speak again, using anything other than an artificial voice that bears no resemblance to the original. Recently, a Scotland-based company called CereProc used archival recordings to recreate an artificial voice that sounds like Ebert. Although it is still in beta, it even has the potential to eventually take on emotional inflection. CereProc is “an advanced voice synthesis company… [which] creates customized text-to-speech software. Instead of producing flat computerized voices, the company says its voices include realistic, animated and emotional dimensions.” (source)
The company undertakes a great deal of research on, what they call, the emotional continuum to stimulate realistic emotional states in voice reproductions:
CereVoice uses two separate techniques to simulate emotional states. The first is to select tense or calm voice quality. This compares closely with the perception of negative and positive emotional states (however, it also has an active/passive effect to some extent). The second is to use digital signal processing (DSP) techniques to alter the speech to active or passive states. Active states involve: faster speech rate, higher volume and higher pitch, Passive states involve: slower speech rate, lower volume and lower pitch. (source)
Pretty inspiring stuff!