top | item 23966952

(no title)

sidthekid | 5 years ago

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?

discuss

order

mensetmanusman|5 years ago

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|5 years ago

Generation is a much harder problem than discrimination though.

grogenaut|5 years ago

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