An Initial Investigation for Detecting Vocoder Fingerprints of Fake Audio
This addresses the need for countermeasures in fake audio detection by identifying the source model, but it is incremental as it builds on existing detection efforts.
The paper tackles the problem of identifying which vocoder generated a fake audio, proposing a new detection task for vocoder fingerprints and showing through t-SNE visualization that different vocoders produce distinct fingerprints.
Many effective attempts have been made for fake audio detection. However, they can only provide detection results but no countermeasures to curb this harm. For many related practical applications, what model or algorithm generated the fake audio also is needed. Therefore, We propose a new problem for detecting vocoder fingerprints of fake audio. Experiments are conducted on the datasets synthesized by eight state-of-the-art vocoders. We have preliminarily explored the features and model architectures. The t-SNE visualization shows that different vocoders generate distinct vocoder fingerprints.