I hadn’t quite gotten out of bed this morning when I heard this segment on the radio about Trade School.
If you’ve been following my posts here about the school, you may find this basic report to be redundant, but there’s something very nice about hearing Caroline (and Louise I think?) speaking on the radio.
Apparently he revealed his new voice during an Oprah taping. His wife Chaz is hearing it for the first time in this video clip. It’s heartwarming and the guy is obviously very brave for going this route, but it also feels to me like an intrusion on their private moment.
Well, kind of, thanks to a company that custom builds text-to-speech voices. Ebert’s new voice is compiled from his vast accumulated archive of reviews and commentary tracks.
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.”
CereProc is now blending in my audio snippets for “Casablanca,” where I sound enthusiastic, and “Floating Weeds,” where I sound calm and respectful. It’s nice to think of all these great movies sloshing around and coming out as my voice.
Link (See also)