3,839
edits
Synthetic human-like fakes: Difference between revisions
→2010's: + 2018 science and demonstration of the sound-like-anyone-machine by Google researchers that steals a voice from 5 second sample, presented at the 2018 w:Conference on Neural Information Processing Systems + minor fmt
Juho Kunsola (talk | contribs) (→2010's: + 2017 science. At wSIGGRAPH 2017 Supasorn Suwajanakorn et al. of the w:University of Washington presented an audio driven digital look-alike of upper torso of Barack Obama. It was driven only by a voice track as source data for the animation after the training phase to acquire w:lip sync and wider facial information from w:training material consisting 2D videos with audio had been completed. + wrote this in Wikipedia back in the day) |
Juho Kunsola (talk | contribs) (→2010's: + 2018 science and demonstration of the sound-like-anyone-machine by Google researchers that steals a voice from 5 second sample, presented at the 2018 w:Conference on Neural Information Processing Systems + minor fmt) |
||
| Line 240: | Line 240: | ||
[[File:Adobe Corporate Logo.png|thumb|right|300px|[[w:Adobe Inc.]]'s logo. We can thank Adobe for publicly demonstrating their sound-like-anyone machine before an implementation was sold to criminal organizations.]] | [[File:Adobe Corporate Logo.png|thumb|right|300px|[[w:Adobe Inc.]]'s logo. We can thank Adobe for publicly demonstrating their sound-like-anyone machine before an implementation was sold to criminal organizations.]] | ||
* ''' | * '''<font color="red">2018</font>''' | <font color="red">science</font> and demonstration | '''[[w:Adobe Inc.]]''' publicly demonstrates '''[[w:Adobe Voco]]''', a '''sound-like-anyone machine''' [https://www.youtube.com/watch?v=I3l4XLZ59iw '#VoCo. Adobe Audio Manipulator Sneak Peak with Jordan Peele | Adobe Creative Cloud' on Youtube]. THe original Adobe Voco required '''20 minutes''' of sample '''to thieve a voice'''. <font color="green">'''Relevancy: certain'''</font>. | ||
* '''2016''' | music video |'''[https://www.youtube.com/watch?v=ElvLZMsYXlo 'Voodoo In My Blood' (official music video) by Massive Attack on Youtube]''' by [[w:Massive Attack]] and featuring [[w:Tricky]] from the album [[w:Ritual Spirit]]. Relevancy: '''How many machines''' can you see in the same frame at times? If you answered one, look harder and make a more educated guess. | * '''2016''' | music video |'''[https://www.youtube.com/watch?v=ElvLZMsYXlo 'Voodoo In My Blood' (official music video) by Massive Attack on Youtube]''' by [[w:Massive Attack]] and featuring [[w:Tricky]] from the album [[w:Ritual Spirit]]. Relevancy: '''How many machines''' can you see in the same frame at times? If you answered one, look harder and make a more educated guess. | ||
| Line 261: | Line 261: | ||
| access-date = 2020-06-26 }} | | access-date = 2020-06-26 }} | ||
</ref> <font color="green">'''Relevancy: certain'''</font> | </ref> <font color="green">'''Relevancy: certain'''</font> | ||
* '''<font color="red">2018</font>''' | <font color="red">science</font> and <font color="red">demonstration</font> | The work [http://papers.nips.cc/paper/7700-transfer-learning-from-speaker-verification-to-multispeaker-text-to-speech-synthesis 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis'] ([https://arxiv.org/abs/1806.04558 at arXiv.org]) was presented at the 2018 [[w:Conference on Neural Information Processing Systems]] (NeurIPS). The pre-trained model is able to steal voices from a sample of only '''5 seconds''' with almost convincing results. | |||
== Footnotes == | == Footnotes == | ||