Harder or Different? Understanding Generalization of Audio Deepfake Detection
원문 초록
Recent research has highlighted a key issue in speech deepfake detection: models trained on one set of deepfakes perform poorly on others. The question arises: is this due to the continuously improving quality of Text-to-Speech (TTS) models, i.e., are newer DeepFakes just 'harder' to detect? Or, is it because deepfakes generated with one model are fundamentally different to those generated using another model? We answer this question by decomposing the performance gap between in-domain and out-of-domain test data into 'hardness' and 'difference' components. Experiments performed using ASVspoof databases indicate that the hardness component is practically negligible, with the performance gap being attributed primarily to the difference component. This has direct implications for real-world deepfake detection, highlighting that merely increasing model capacity, the currently-dominant research trend, may not effectively address the generalization challenge.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Few-Shot Speech Deepfake Detection Adaptation with Gaussian Processes
Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation
Bts-e: Audio deepfake detection using breathing-talking-silence encoder
BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset
End-to-end Audio Deepfake Detection from RAW Waveforms: a RawNet-Based Approach with Cross-Dataset Evaluation
Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception
토론
이 논문과 연결된 포럼 글이 아직 없습니다.