News for hackers. Stuff that matters.
Re:WaveNet: A Generative Model for Raw Audio by swsieber on Thursday September 08, 2016 @04:42PM (#12457090)
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...

Re:WaveNet: A Generative Model for Raw Audio by erichocean on Thursday September 08, 2016 @04:43PM (#12457109)
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.

Re:WaveNet: A Generative Model for Raw Audio by StavrosK on Thursday September 08, 2016 @06:34PM (#12458009)
Really? I haven't trusted anything recorded in years.
Re:WaveNet: A Generative Model for Raw Audio by copperx on Friday September 09, 2016 @11:45PM (#12467583)
Speech production is incredibly hard to fake at the moment.
Re:WaveNet: A Generative Model for Raw Audio by sangnoir on Sunday September 11, 2016 @05:08AM (#12472582)
> Speech production is incredibly hard to fake at the moment.

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

Re:WaveNet: A Generative Model for Raw Audio by mirimir on Friday September 09, 2016 @03:46AM (#12460297)
Or transmitted from one place to another :(