Cross-Domain Audio Deepfake Detection: Dataset and Analysis
Abstract: Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy. Recent zero-shot text-to-speech (TTS) models pose higher risks as they can clone voices with a single utterance. However, the existing ADD datasets are outdated, leading to suboptimal generalization of detection models. In this paper, we construct a new cross-domain ADD dataset comprising over 300 hours of speech data that is generated by five advanced zero-shot TTS models. To simulate real-world scenarios, we employ diverse attack methods and audio prompts from different datasets. Experiments show that, through novel attack-augmented training, the Wav2Vec2-large and Whisper-medium models achieve equal error rates of 4.1% and 6.5% respectively. Additionally, we demonstrate our models' outstanding few-shot ADD ability by fine-tuning with just one minute of target-domain data. Nonetheless, neural codec compressors greatly affect the detection accuracy, necessitating further research.
Paper Type: Short
Research Area: Speech Recognition, Text-to-Speech and Spoken Language Understanding
Research Area Keywords: Text-to-Speech, Voice Cloning, Deepfake Detection
Contribution Types: Model analysis & interpretability, Reproduction study, Approaches to low-resource settings, Data resources, Data analysis, Position papers
Languages Studied: English
Submission Number: 41
Loading