On: WaveNet: A Generative Model for Raw Audio

[swsieber]

Oh, pair this with facial mapping[1] and you pretty much have an "impersonate any famous person" system.

[1] http://www.graphics.stanford.edu/~niessner/thies2016face.htm...

[erichocean → swsieber]

Yup, I work in virtual filmmaking and there are tons of way to use this stuff.

I give us 10-15 years before it's not possible to trust anything you see or hear that's recorded.

[stavros → erichocean]

Really? I haven't trusted anything recorded in years.

[copperx → stavros]

Speech production is incredibly hard to fake at the moment.

[sangnoir → copperx]

> Speech production is incredibly hard to fake at the moment.

Sound-alikes have been used in the music industry since forever.

[mirimir → erichocean]

Or transmitted from one place to another :(