News for hackers. Stuff that matters.
Re:WaveNet: A Generative Model for Raw Audio by itcrowd on Thursday September 08, 2016 @06:56PM (#12458172)
Another fun fact: this actually happens with (cell) phone calls.

You don't send your speech over the line, instead you send some parameters over the line which are then, at the receiving end, fed into a white(-ish) noise generator to recover the speech.

Edit: not by using a neural net or deep learning, of course.

Re:WaveNet: A Generative Model for Raw Audio by JonnieCache on Thursday September 08, 2016 @07:06PM (#12458248)
In case anyone is wondering, the technique is called linear predictive coding.
Re:WaveNet: A Generative Model for Raw Audio by AstralStorm on Friday September 09, 2016 @03:32AM (#12460243)
Predictive coding. Linear is a specific variant of it used in older codecs.
Re:WaveNet: A Generative Model for Raw Audio by VikingCoder on Friday September 09, 2016 @11:56AM (#12463378)
What's the difference in bandwidth?