3,839
edits
Synthetic human-like fakes: Difference between revisions
major reorg of the media
Juho Kunsola (talk | contribs) (→Audio samples from 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis' by Google Research: + giving link to the transcluded iframe contents) |
Juho Kunsola (talk | contribs) (major reorg of the media) |
||
| Line 70: | Line 70: | ||
---- | ---- | ||
= Digital sound-alikes = | = Digital sound-alikes = | ||
Living people can defend¹ themselves against digital sound-alike by denying the things the digital sound-alike says if they are presented to the target, but dead people cannot. Digital sound-alikes offer criminals new disinformation attack vectors and wreak havoc on provability. | Living people can defend¹ themselves against digital sound-alike by denying the things the digital sound-alike says if they are presented to the target, but dead people cannot. Digital sound-alikes offer criminals new disinformation attack vectors and wreak havoc on provability. | ||
| Line 86: | Line 85: | ||
* As of '''2019''' Symantec research knows of 3 cases where digital sound-alike technology '''has been used for crimes'''.<ref name="WaPo2019"> | * As of '''2019''' Symantec research knows of 3 cases where digital sound-alike technology '''has been used for crimes'''.<ref name="WaPo2019"> | ||
https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/</ref> | https://www.washingtonpost.com/technology/2019/09/04/an-artificial-intelligence-first-voice-mimicking-software-reportedly-used-major-theft/</ref> | ||
---- | ---- | ||
| Line 119: | Line 116: | ||
---- | ---- | ||
= | == 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis' 2018 by Google Research == | ||
= | |||
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. | 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}} | {{#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. | |||
{{#ev:youtube|0sR1rU3gLzQ|640px|right|Video 'This AI Clones Your Voice After Listening for 5 Seconds' by '2 minute papers' describes the voice thieving machine by Google Research in [[w:NeurIPS|NeurIPS]] 2018.}} | |||
[[File:Spectrogram-19thC.png|thumb|right|640px|A [[w:spectrogram|spectrogram]] of a male voice saying 'nineteenth century']] | |||
= Footnotes = | = Footnotes = | ||
<references group="footnote" /> | <references group="footnote" /> | ||