3,839
edits
Synthetic human-like fakes: Difference between revisions
m
fmt
Juho Kunsola (talk | contribs) (→2021 digital sound-alike enabled fraud: + This case came into light when Forbes saw a document where the U.A.E. financial authorities were seeking administrative assistance from the US authorities towards the end of recovering a small portion of the defrauded money that had been sent to bank accounts in the USA) |
Juho Kunsola (talk | contribs) m (fmt) |
||
| Line 116: | Line 116: | ||
Then in '''2018''' at the '''[[w:Conference on Neural Information Processing Systems]]''' (NeurIPS) the work [http://papers.nips.cc/paper/7700-transfer-learning-from-speaker-verification-to-multispeaker-text-to-speech-synthesis 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis'] ([https://arxiv.org/abs/1806.04558 at arXiv.org]) was presented. The pre-trained model is able to steal voices from a sample of only '''5 seconds''' with almost convincing results | Then in '''2018''' at the '''[[w:Conference on Neural Information Processing Systems]]''' (NeurIPS) the work [http://papers.nips.cc/paper/7700-transfer-learning-from-speaker-verification-to-multispeaker-text-to-speech-synthesis 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis'] ([https://arxiv.org/abs/1806.04558 at arXiv.org]) was presented. The pre-trained model is able to steal voices from a sample of only '''5 seconds''' with almost convincing results | ||
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}} | ||