3,839
edits
Synthetic human-like fakes: Difference between revisions
+ <section begin=GoogleTransferLearning2018 /> + <section end=GoogleTransferLearning2018 />
Juho Kunsola (talk | contribs) (transcluded a quote with {{#lst:Quotes|MatrixTrad}}) |
Juho Kunsola (talk | contribs) (+ <section begin=GoogleTransferLearning2018 /> + <section end=GoogleTransferLearning2018 />) |
||
| Line 146: | Line 146: | ||
=== 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis' 2018 by Google Research (external transclusion) === | === 'Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis' 2018 by Google Research (external transclusion) === | ||
<section begin=GoogleTransferLearning2018 /> | |||
* In the '''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 | * In the '''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 | ||
| Line 154: | Line 154: | ||
The Iframe above 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 above 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. | ||
<section end=GoogleTransferLearning2018 /> | |||
=== Digital sing-alikes === | === Digital sing-alikes === | ||