821
edits
Please sign and share the petition 'Tighten regulation on taking, making and faking explicit images' at Change.org initiated by Helen Mort to the w:Law Commission (England and Wales) to properly update UK laws against synthetic filth. Only name and email required to support, no nationality requirement. See Current and possible laws and their application @ #SSF! wiki for more info on the struggle for laws to protect humans.
Juho Kunsola (talk | contribs) (→Syntheses: + Lyrebird.ai (listen)) |
Juho Kunsola (talk | contribs) (+ === Wikipedia links about digital look-alikes === + w:Human image synthesis) |
||
(2 intermediate revisions by the same user not shown) | |||
Line 10: | Line 10: | ||
* [http://www.niessnerlab.org/projects/thies2016face.html A 2016 paper (with videos) on the semi-real-time 2D video manipulation with gesture gesture forcing and lip sync forcing synthesis] by Thies et al 2016, Stanford. | * [http://www.niessnerlab.org/projects/thies2016face.html A 2016 paper (with videos) on the semi-real-time 2D video manipulation with gesture gesture forcing and lip sync forcing synthesis] by Thies et al 2016, Stanford. | ||
=== | === Wikipedia links about digital look-alikes === | ||
* [[w:Human image synthesis]] | |||
== Digital sound-alikes == | |||
=== Wikipedia links about digital sound alikes === | === Wikipedia links about digital sound alikes === | ||
* [[w:Adobe Voco]] | * [[w:Adobe Voco]] | ||
* Google [[w:WaveNet]] | * Google [[w:WaveNet]] | ||
=== Other contenders to create digital sound-alikes === | |||
As of 2019, these speech synthesis in most use scenarios does not yet fool a human because the results contain tell tale signs that give it away as a speech synthesizer. | |||
* https://cstr-edinburgh.github.io/merlin/ - free opensource voice synthesis framework | |||
* [https://lyrebird.ai/ Lyrebird.ai] [https://www.youtube.com/watch?v=xxDBlZu__Xk (listen)] | |||
* https://candyvoice.com/ and their eery phone app and other useful services. | |||
== GANs == | == GANs == |