Synthetic human-like fakes: Difference between revisions

Jump to navigation Jump to search
moved content around unchanged
m (stating in heading that 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis' is an external transclusion)
(moved content around unchanged)
Line 90: Line 90:


----
----
=== Examples of speech synthesis software not quite able to fool a human yet ===
=== 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis' 2018 by Google Research (external transclusion) ===
Some other contenders to create digital sound-alikes are though, as of 2019, their 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://lyrebird.ai/ Lyrebird.ai]''' [https://www.youtube.com/watch?v=xxDBlZu__Xk (listen)]
* '''[https://candyvoice.com/ CandyVoice.com]''' [https://candyvoice.com/demos/voice-conversion (test with your choice of text)]
* '''[https://cstr-edinburgh.github.io/merlin/ Merlin]''', a [[w:neural network]] based speech synthesis system by the Centre for Speech Technology Research at the [[w:University of Edinburgh]]


The Iframe below is transcluded from [https://google.github.io/tacotron/publications/speaker_adaptation/ 'Audio samples from "Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis"' at google.gituhub.io], the audio samples of a sound-like-anyone machine presented as at the 2018 [[w:NeurIPS]] conference by Google researchers.
{{#Widget:Iframe - Audio samples from Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis by Google Research}}


=== Documented digital sound-alike attacks ===
=== Documented digital sound-alike attacks ===
Line 114: Line 111:


Thus it is high time to act and to '''[[Law proposals to ban covert modeling|criminalize the covert modeling of human appearance and voice!]]'''
Thus it is high time to act and to '''[[Law proposals to ban covert modeling|criminalize the covert modeling of human appearance and voice!]]'''
=== Examples of speech synthesis software not quite able to fool a human yet ===
Some other contenders to create digital sound-alikes are though, as of 2019, their 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://lyrebird.ai/ Lyrebird.ai]''' [https://www.youtube.com/watch?v=xxDBlZu__Xk (listen)]
* '''[https://candyvoice.com/ CandyVoice.com]''' [https://candyvoice.com/demos/voice-conversion (test with your choice of text)]
* '''[https://cstr-edinburgh.github.io/merlin/ Merlin]''', a [[w:neural network]] based speech synthesis system by the Centre for Speech Technology Research at the [[w:University of Edinburgh]]


----
----
Footnote 1. Whether a suspect can defend against faked synthetic speech that sounds like him/her depends on how up-to-date the judiciary is. If no information and instructions about digital sound-alikes have been given to the judiciary, they likely will not believe the defense of denying that the recording is of the suspect's voice.
Footnote 1. Whether a suspect can defend against faked synthetic speech that sounds like him/her depends on how up-to-date the judiciary is. If no information and instructions about digital sound-alikes have been given to the judiciary, they likely will not believe the defense of denying that the recording is of the suspect's voice.
----
----
=== 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis' 2018 by Google Research (external transclusion) ===
The Iframe below is transcluded from [https://google.github.io/tacotron/publications/speaker_adaptation/ 'Audio samples from "Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis"' at google.gituhub.io], the audio samples of a sound-like-anyone machine presented as at the 2018 [[w:NeurIPS]] conference by Google researchers.
{{#Widget:Iframe - Audio samples from Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis by Google Research}}
The below video 'This AI Clones Your Voice After Listening for 5 Seconds' by '2 minute papers' describes the voice thieving machine presented by Google Research in [[w:NeurIPS|NeurIPS]] 2018.
The below video 'This AI Clones Your Voice After Listening for 5 Seconds' by '2 minute papers' describes the voice thieving machine presented by Google Research in [[w:NeurIPS|NeurIPS]] 2018.


We use only those cookies necessary for the functioning of the wiki and we will never sell your data. All data is stored in the EU.

Navigation menu