2024
SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection
NeurIPS 2024poster
Audio deepfake detection (ADD) is crucial to combat the misuse of speech synthesized by generative AI models. Existing ADD models suffer from generalization issues to unseen attacks, with a large performance discrepancy between in-domain and out-of-domain data. Moreover, the black-box nature of exis…