I bet this only reliably works on undistorted, uncompressed audio. Just throw some distortion over a HQ deepfake audio and try an adversarial network based on the research of these scientists. At some point we might have to switch to fully digitally signed communication with specially trusted devices.
I bet this only reliably works on undistorted, uncompressed audio. Just throw some distortion over a HQ deepfake audio and try an adversarial network based on the research of these scientists. At some point we might have to switch to fully digitally signed communication with specially trusted devices.