Scotish CereProc company trained a neural network to predict how Mr Dupree would talk, using samples from his old voice recordings A new voice was created for him. In order to create a voice for someone, the individual needs to read out a script for 30 hours in order to gather enough data. After, the technology is used to predict and imitate the person’s speech patterns. It can take a month to produce just one voice but after developing its own technologies CereProc can generate a voice in just a few days at an affordable price of £500.
The artificial intelligence system slices each word read out by an individual into 100 tiny pieces and understands how basic phonetics work in a person’s voice. “AI techniques work quite well on small constrained problems, and learning to model speech is something deep neural nets can do really well,” Chris Pidcock, CereProc’s chief technical officer and co-founder, told to media. Mr Dupree has been covering political news from Congress in Washington DC for the past 35 years. He had gone off the air completely, because he could not present the stories he had written. Thanks to the computer-generated voice produced by CereProc, from Monday, 25 June he will be heard again by WSB Atlanta listeners.