The first AI-powered synthetic media like deepfakes are already starting to happen. Building tools that can accurately discern between real and fake media is an increasingly urgent matter. Weve built a detector system built to discern between audio deepfake audio examples. The detector uses visual representations of audio clips called spectrograms, which are also used to train speech synthesis models. We’ve also included a walkthrough of the code to help people develop their own fake voice detection models to help mitigate a real-world problem.”]
Source: https://medium.com/dessa-news/detecting-audio-deepfakes-f2edfd8e2b35