Adaptive Fake Audio Detection with Low-Rank Model Squeezing
This addresses the need for efficient and robust fake audio detection in security applications, though it is incremental as it builds on existing adaptation methods.
The paper tackles the problem of detecting emerging fake audio types without impairing detection of known types, proposing low-rank adaptation matrices that preserve accuracy for known types while reducing storage and error rates compared to finetuning.
The rapid advancement of spoofing algorithms necessitates the development of robust detection methods capable of accurately identifying emerging fake audio. Traditional approaches, such as finetuning on new datasets containing these novel spoofing algorithms, are computationally intensive and pose a risk of impairing the acquired knowledge of known fake audio types. To address these challenges, this paper proposes an innovative approach that mitigates the limitations associated with finetuning. We introduce the concept of training low-rank adaptation matrices tailored specifically to the newly emerging fake audio types. During the inference stage, these adaptation matrices are combined with the existing model to generate the final prediction output. Extensive experimentation is conducted to evaluate the efficacy of the proposed method. The results demonstrate that our approach effectively preserves the prediction accuracy of the existing model for known fake audio types. Furthermore, our approach offers several advantages, including reduced storage memory requirements and lower equal error rates compared to conventional finetuning methods, particularly on specific spoofing algorithms.