News for hackers. Stuff that matters.
Re:AI produces realistic sounds that fool humans by macawfish on Monday June 13, 2016 @10:52AM (#11894302)
They trained the algorithm to watch the stick and play sounds from the database where the stick moved similarly.

But the title makes it seem like the algorithm is synthesizing the sounds from scratch!

Re:AI produces realistic sounds that fool humans by colordrops on Monday June 13, 2016 @04:50PM (#11897509)
Exactly, most of the work here is video processing - analyzing a portion of one video, then finding another video clip that has similar characteristics. Then they copy the sound from the second clip into the first clip. But they could be copying any metadata, not just sound. This isn't really about sound _at all_.
Re:AI produces realistic sounds that fool humans by visarga on Tuesday June 14, 2016 @02:03AM (#11900102)
> But the title makes it seem like the algorithm is synthesizing the sounds from scratch!

It does. If you read the paper, they say that first they went with matching sounds from a database, but later turned on to full synthesis.

Reference: look for "parametric synthesis" in the paper https://arxiv.org/pdf/1512.08512v2.pdf

Re:AI produces realistic sounds that fool humans by a1k0n on Monday June 13, 2016 @11:11AM (#11894474)
They do both; there's a parametric synthesis module later on in the video. It doesn't work all that well for water.
Re:AI produces realistic sounds that fool humans by 542458 on Monday June 13, 2016 @11:14AM (#11894510)
They can do pure parametric synthesis as well, but it's not nearly as convincing so most of the video is devoted to the more convincing match method. FWIW, constructing realistic sounds from first principles is much more difficult than you'd think.

> where the stick moved similarly

where the stick moved similarly and was hitting similar things, which is a non-trivial task.

Re:AI produces realistic sounds that fool humans by tuewocnc on Monday June 13, 2016 @01:14PM (#11895490)
yes, it would have to learn to simulate the physics of the system to match the video, which would be cool
Re:AI produces realistic sounds that fool humans by c3534l on Monday June 13, 2016 @02:10PM (#11895887)
And for what it is, it's really unimpressive. It's a cool idea and all, just with disappointing results.
Re:AI produces realistic sounds that fool humans by jobigoud on Monday June 13, 2016 @11:12AM (#11894482)
They also train for the material the stick is hitting. But yeah, it's sound transfer, not synthesis from scratch.

But that's also the approach of current speech synthesis algorithms and works better than trying to create the waveform from scratch.

Re:AI produces realistic sounds that fool humans by mwcampbell on Monday June 13, 2016 @06:01PM (#11898081)
> But that's also the approach of current speech synthesis algorithms and works better than trying to create the waveform from scratch.

I don't think it's that simple. Speech synthesis by concatenation does produce more natural-sounding results, at least until you notice its quirks, so casual users tend to prefer it. But I know some heavy speech synthesis users, specifically blind programmers and power-users, and they tend to prefer parametric synthesis, because it's more intelligible at high speeds.

Re:AI produces realistic sounds that fool humans by jordache on Monday June 13, 2016 @12:14PM (#11895032)
Yes the title may give that impression, but the video explains clearly the source of the audio