Meta found a way to secretly watermark deepfake audio

Researchers have found a way to imperceptibly watermark fake audio

"Proactive detection of AI-generated speech. We embed an imperceptible watermark in the audio, which can be used to detect if a speech is AI-generated and identify the model that generated it."

The rapid advancement of AI voice synthesis technologies has enabled the creation of extremely realistic fake human speech. However, this also opens up concerning possibilities of voice cloning, deepfakes, and other forms of audio manipulation (this recent fake Biden robocall being the first example that comes to mind).

Robust new detection methods are needed to find and segregate audio deepfakes from real recordings. In this post, we'll take a look at a novel technique from Facebook Research called AudioSeal (github, paper) that tackles this problem by imperceptibly watermarking AI-generated speech. We'll see how it works and also take a look at some applications and limitations. Let's go!