News for hackers. Stuff that matters.
Re:Speech2Face: Learning the Face Behind a Voice by jcims on Sunday May 26, 2019 @04:45PM (#20017387)
Or it could be that a goatee physically influences the sound of the voice in a way that is perceptible to the algorithm. For example, damping transmission through the skin and attenuating reflections off the chin and upper pip.
Re:Speech2Face: Learning the Face Behind a Voice by anigbrowl on Sunday May 26, 2019 @05:34PM (#20017693)
It doesn't. I worked as a sound engineer in film for a decade and I'm extremely forensically minded.
Re:Speech2Face: Learning the Face Behind a Voice by jcims on Sunday May 26, 2019 @08:02PM (#20018461)
You motivated me to investigate.

Extreme example, compare audio at 4m and 21m - https://www.youtube.com/watch?v=6dbQ2OA4SRA

Clearly a different top end.

Did a little tinkering in Audacity and with the beard there's a standard roll off from 3khz to 10khz. Without there's a weird flat spot in the same area (both are averaged over 20 seconds or so)

Re:Speech2Face: Learning the Face Behind a Voice by solarkraft on Sunday May 26, 2019 @06:31PM (#20017988)
But are you absolutely sure there aren't tiny, tiny differences? I don't think it's likely, but how can you be so sure?
Re:Speech2Face: Learning the Face Behind a Voice by anigbrowl on Sunday May 26, 2019 @08:55PM (#20018667)
I'm dubious because of the frequency range of audio recordings (especially post compression on Youtube) and the size of cells, even large ones like hair follicles.
Re:Speech2Face: Learning the Face Behind a Voice by ClassyJacket on Sunday May 26, 2019 @05:46PM (#20017757)
You can't know this.
Re:Speech2Face: Learning the Face Behind a Voice by drusepth on Sunday May 26, 2019 @06:35PM (#20018014)
How do you know he can't know this?
Re:Speech2Face: Learning the Face Behind a Voice by wanderfowl on Sunday May 26, 2019 @07:28PM (#20018272)
This feels very unlikely. Hairs are thin, non-absorptive, and spaced far enough apart to avoid much absorption. Unless it were an exceptionally bushy and thick goatee, I don't imagine there's much effect.
Re:Speech2Face: Learning the Face Behind a Voice by jpfed on Sunday May 26, 2019 @11:02PM (#20019113)
They trained this model on Youtube videos. I'd be surprised if whatever fine differences goatees may induce didn't get crushed away by Youtube's lossy compression.