TTS watermarks: Difference between revisions

From Voice Technology Wiki
Jump to navigation Jump to search
m (Added some Twitter ideas.)
m (Added new thoughts from Erogol about watermarks.)
 
Line 4: Line 4:
Based on Erogol's idea from Coqui there should be a way to identify deep-fakes in voice context. After some Twitter chatting<ref>https://twitter.com/erogol/status/1464412634783043585?s=20</ref> there seems one thing without doubt: "It's the old story between hacker and the people trying to prevent misusage".
Based on Erogol's idea from Coqui there should be a way to identify deep-fakes in voice context. After some Twitter chatting<ref>https://twitter.com/erogol/status/1464412634783043585?s=20</ref> there seems one thing without doubt: "It's the old story between hacker and the people trying to prevent misusage".


==Possible techniques==
==Possible techniques<ref>https://github.com/coqui-ai/TTS/discussions/1036#discussioncomment-1863431</ref>==
What kind of techniques are useful for what and what's the pros and cons?
What kind of techniques are useful for what and what's the pros and cons:


* Watermark
=== Watermark in TTS output ===
* ...
Easy to analyse / reproduce using original sourcecode.
 
=== Watermark in TTS dataset ===
Models can learn to reproduce watermark without seeing anything on that in the code.


== References ==
== References ==
<references />
<references />

Latest revision as of 19:49, 23 December 2021


Preventing deep fakes[edit | edit source]

Based on Erogol's idea from Coqui there should be a way to identify deep-fakes in voice context. After some Twitter chatting[1] there seems one thing without doubt: "It's the old story between hacker and the people trying to prevent misusage".

Possible techniques[2][edit | edit source]

What kind of techniques are useful for what and what's the pros and cons:

Watermark in TTS output[edit | edit source]

Easy to analyse / reproduce using original sourcecode.

Watermark in TTS dataset[edit | edit source]

Models can learn to reproduce watermark without seeing anything on that in the code.

References[edit | edit source]