News for hackers. Stuff that matters.

A comment on The Rise of Synthetic Audio Deepfakes.

Re:The Rise of Synthetic Audio Deepfakes by sidthekid on Monday July 27, 2020 @12:59PM (#23966952)
The images of spectrogram analysis between the real and fake voices seemed to be distinguishable by the human eye. Can a image model be trained to detect fake voice spectrograms based on pitch and tone choppiness?
[ Parent | on HN ]
Re:The Rise of Synthetic Audio Deepfakes by mensetmanusman on Monday July 27, 2020 @01:25PM (#23967269)
The issue is that if you can measure it, you can train an AI to beat the other AI detecting it.

As Pilate said: ‘Quid est veritas?‘

[ Parent | on HN ]
Re:The Rise of Synthetic Audio Deepfakes by deepnotderp on Monday July 27, 2020 @01:55PM (#23967632)
Generation is a much harder problem than discrimination though.
[ Parent | on HN ]
Re:The Rise of Synthetic Audio Deepfakes by grogenaut on Monday July 27, 2020 @01:21PM (#23967217)
Would you not just then take this and feed it into the training?
[ Parent | on HN ]