[im] Portraits Based On Someone's Voice

Miklos Peternak peternak at c3.hu
Sat Jun 8 11:32:37 CEST 2019


https://www.abc.net.au/news/2018-09-18/china-social-credit-a-model-citizen-in-a-digital-dictatorship/10200278

On 2019. 06. 08. 9:24, János Sugár wrote:
> Portraits Based On Someone's Voice
> _*An Algorithm Generated Eerily Accurate Portraits Based Only On 
> Someone's Voice*_ 
> <https://gizmodo.com/an-algorithm-generated-eerily-accurate-portraits-based-1835327568>
> *
> *
> MIT researchers published a paper last month called Speech2Face: 
> Learning the Face Behind a Voice which explores how an algorithm can 
> generate a face based on a short audio recording of that person. It's 
> not an exact depiction of the speaker, but based on images in the 
> paper, the system was able to create an image of a front-facing face 
> with a neutral expression with accurate gender, race, and age.
> <https://arxiv.org/pdf/1905.09773.pdf>
> https://gizmodo.com/an-algorithm-generated-eerily-accurate-portraits-based-1835327568 
> <https://gizmodo.com/an-algorithm-generated-eerily-accurate-portraits-based-1835327568>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.c3.hu/pipermail/intermedia-l/attachments/20190608/d7b8d4b7/attachment.htm>


More information about the Intermedia-l mailing list