Comment Re:Are there any examples? (Score 1) 16
I'm finding it a tad hard to believe an AI can guess someone's voice correctly from a photograph.
Then you're going to be gobsmacked by how they can reconstruct a person's physical appearance from just their skull bones.
Back to the topic at hand, it's not that difficult to theorize about reproducing the voice's tonal characteristics. A person's voice is influenced by their skull shape, jaw size, sinus cavities, muscle structure, neck length, etc. With millions of examples to match voice intonation to physical appearance, they can make a reasonable approximation of a person's voice tonal sound.
What they would have problems with is regional accents. A person growing up in NYC, Dallas, LA, Atlanta, and Bangor, ME will have different accents that would be harder to replicate.