[sidthekid]

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?

[mensetmanusman]

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?‘

[deepnotderp]

Generation is a much harder problem than discrimination though.

[grogenaut]

Would you not just then take this and feed it into the training?