News for hackers. Stuff that matters.

A comment on Scammers deepfake CEO’s voice to talk underling into $243k transfer?.

Re:Scammers deepfake CEO’s voice to talk underling into $243... by dazhengca on Thursday November 14, 2019 @11:38AM (#21536822)
How could there be enough samples of his voice? Seems like quite a jump to “it was a deep fake” unless there’s more info they haven’t revealed
[ Parent | on HN ]
Re:Scammers deepfake CEO’s voice to talk underling into $243... by Dockson on Thursday November 14, 2019 @11:43AM (#21536854)
Five seconds is enough https://news.ycombinator.com/item?id=21525878
[ Parent | on HN ]
Re:Scammers deepfake CEO’s voice to talk underling into $243... by ry4nolson on Thursday November 14, 2019 @11:51AM (#21536933)
From yesterday: https://news.ycombinator.com/item?id=21525878

Only requires 5 seconds of voice audio to synthesize believable speech.

[ Parent | on HN ]
Re:Scammers deepfake CEO’s voice to talk underling into $243... by danso on Thursday November 14, 2019 @12:51PM (#21537590)
The cadence of the synthesized voices are still noticeably artificial, even for the short demo phrases. This is not to say this isn't impressive. But how much does this method improve when it isn't constrained by a 5-second sample? If we feed it several hours of public speeches from Martin Luther King Jr, or hell, tens of hours of audio from President Obama or Trump – will it have the same artificial cadence, even if the tone and pitch of the imitated voice is accurate?
[ Parent | on HN ]