Forensic deepfake audio detection using segmental speech features
This addresses the problem of detecting manipulated audio for forensic and security applications, offering a new perspective but is incremental in leveraging existing features.
The study tackled deepfake audio detection by using segmental speech features, which are interpretable and hard for deepfakes to replicate, and found that certain features from forensic voice comparison were effective while global features were not.
This study explores the potential of using acoustic features of segmental speech sounds to detect deepfake audio. These features are highly interpretable because of their close relationship with human articulatory processes and are expected to be more difficult for deepfake models to replicate. The results demonstrate that certain segmental features commonly used in forensic voice comparison (FVC) are effective in identifying deep-fakes, whereas some global features provide little value. These findings underscore the need to approach audio deepfake detection using methods that are distinct from those employed in traditional FVC, and offer a new perspective on leveraging segmental features for this purpose.