A General Model for Deepfake Speech Detection: Diverse Bonafide Resources or Diverse AI-Based Generators
For researchers building deepfake speech detectors, this work identifies the critical importance of balancing bonafide and fake data diversity for model generalization.
The paper investigates how the diversity of bonafide speech resources and AI-based generators affects deepfake speech detection model generality. Experiments show that balancing these factors in training data is key to achieving a general model, as demonstrated by cross-dataset evaluation.
In this paper, we analyze two main factors of Bonafide Resource (BR) or AI-based Generator (AG) which affect the performance and the generality of a Deepfake Speech Detection (DSD) model. To this end, we first propose a deep-learning based model, referred to as the baseline. Then, we conducted experiments on the baseline by which we indicate how Bonafide Resource (BR) and AI-based Generator (AG) factors affect the threshold score used to detect fake or bonafide input audio in the inference process. Given the experimental results, a dataset, which re-uses public Deepfake Speech Detection (DSD) datasets and shows a balance between Bonafide Resource (BR) or AI-based Generator (AG), is proposed. We then train various deep-learning based models on the proposed dataset and conduct cross-dataset evaluation on different benchmark datasets. The cross-dataset evaluation results prove that the balance of Bonafide Resources (BR) and AI-based Generators (AG) is the key factor to train and achieve a general Deepfake Speech Detection (DSD) model.