Film critic Roger Ebert has spent the better part of the last decade battling thyroid cancer, but his last bout took away his lower jaw and ability to speak.
Edinburgh, Scotland-based company CereProc is helping the former “At the Movies” host regain it.
Through its CereVoice product, the five-year-old company offers custom-tailored text-to-speech software that takes previously recorded clips from the patient and patches them together to approximate — in a more natural way — the user’s original voice.
As befits a longtime television show host, CereProf mined Ebert’s tapes and DVD commentaries to create a voice that’s as Ebert-like as possible.
Here’s Ebert describing the process:
This began a back-and-forth process with CereProc, which had to transcribe every recording with perfect accuracy so they could locate every word. The “normal person” may use 5,000 words, not all of them on the same day. A college professor may use 15,000. Shakespeare used more than 25,000, but he was making up a lot of them as he went along.
Anyway, CereProc didn’t need to hear me speaking a specific word in order for my “voice” to say it. They needed lots of words to determine the general idea of how I might say a word. They transcribed and programmed and tweaked and fiddled, and early this February, sent me the files for a beta version of my voice. I played it for Chaz, and she said, yes, she could tell it was me. For one thing it knew exactly how I said “I.”
That’s right: they’re literally piecing together an Ebert soundtrack, word by word, syllable by syllable.
The goal: to offer a more emotional voice that conveys more of a person’s total emotional continuum — or in other words, character.
Ebert recently demonstrated his new voice on The Oprah Winfrey Show. Previously, he had been using the digitized (but rather robotic sounding) American voice programmed in Apple’s Mac OS X.
Here’s an introduction to the company from our siblings at CBS’s The Early Show:
And here’s CereProc chief technical officer Matthew Aylett discussing the technology:
As Aylett says himself, it’s not perfect, but it’s better than an entirely programmed voice, and most certainly a step toward decoding and mastering the constantly evolving nature of the spoken word.
Or as Ebert writes himself: It’s a chance to speak with his wife, talk to his grandchildren, record podcasts, produce new movie commentary, give radio interviews — or just tell a good joke.