TTS watermarks

From Voice Technology Wiki
Jump to navigation Jump to search

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]