English

Enhancing Generalization in Audio Deepfake Detection: A Neural Collapse based Sampling and Training Approach

Sound 2024-04-22 v1 Audio and Speech Processing

Abstract

Generalization in audio deepfake detection presents a significant challenge, with models trained on specific datasets often struggling to detect deepfakes generated under varying conditions and unknown algorithms. While collectively training a model using diverse datasets can enhance its generalization ability, it comes with high computational costs. To address this, we propose a neural collapse-based sampling approach applied to pre-trained models trained on distinct datasets to create a new training database. Using ASVspoof 2019 dataset as a proof-of-concept, we implement pre-trained models with Resnet and ConvNext architectures. Our approach demonstrates comparable generalization on unseen data while being computationally efficient, requiring less training data. Evaluation is conducted using the In-the-wild dataset.

Keywords

Cite

@article{arxiv.2404.13008,
  title  = {Enhancing Generalization in Audio Deepfake Detection: A Neural Collapse based Sampling and Training Approach},
  author = {Mohammed Yousif and Jonat John Mathew and Huzaifa Pallan and Agamjeet Singh Padda and Syed Daniyal Shah and Sara Adamski and Madhu Reddiboina and Arjun Pankajakshan},
  journal= {arXiv preprint arXiv:2404.13008},
  year   = {2024}
}
R2 v1 2026-06-28T16:00:02.756Z