Tuesday, July 5

This is how they created the voice of Val Kilmer in Top Gun: Maverick | Digital Trends Spanish

They say that the very Val Kilmer begged Tom Cruise to include him in the sequel to Top Gun: Maverickto play the iconic Tom “Iceman” Kazansky again.

However, the main difficulty was adapting the character to the current reality of the actor, who was left without a voice and with the use of a typist due to throat cancer that affected him in 2014.

Kilmer gets to say a brief line of dialogue, but his voice was created by artificial intelligence. And 40 models had to be used for this resurrection of his voice.

The actor supplied the company with hours of stock footage featuring his speaking voice which was then fed through the company’s algorithms and turned into a pattern.

“In the end, we generated over 40 different voice models and selected the best, highest quality, and most expressive one,” said John Flynn, CTO and co-founder of Sonantic, in a statement to Forbes. “Those new algorithms are now built into our speech engine, so future customers can take advantage of them automatically as well.”

“I am grateful to the entire team at Sonantic who masterfully restored my voice in a way I never imagined possible,” Kilmer originally said in a statement about the AI. “As human beings, the ability to communicate is at the core of our existence and the side effects of throat cancer have made it difficult for others to understand me. The opportunity to tell my story, in a voice that feels authentic and familiar, is an incredibly special gift.”

What reports Forbes: “After cleaning up old audio recordings of Kilmer, [Sonantic] used a ‘speech engine’ to teach the voice model to speak like Kilmer. The engine had about 10 times less data than it would have been given in a typical project, Sonantic said, and it wasn’t enough. The company then decided to come up with new algorithms that could produce a higher quality voice model using the available data.”

Publisher Recommendations