Fake Speech Wild: Detecting Deepfake Speech on Social Media Platform

Authors: Yuankun Xie, Ruibo Fu, Xiaopeng Wang, Zhiyong Wang, Ya Li, Zhengqi Wen, Haonnan Cheng, Long Ye

Published: 2025-08-14 11:56:30+00:00

AI Summary

This paper introduces the Fake Speech Wild (FSW) dataset, a 254-hour collection of real and deepfake audio from social media platforms, to address the limitations of existing deepfake audio detection models in real-world scenarios. By augmenting public datasets with FSW and employing self-supervised learning-based countermeasures, the authors significantly improve deepfake audio detection performance, achieving an average equal error rate of 3.54%.

Abstract

The rapid advancement of speech generation technology has led to the widespread proliferation of deepfake speech across social media platforms. While deepfake audio countermeasures (CMs) achieve promising results on public datasets, their performance degrades significantly in cross-domain scenarios. To advance CMs for real-world deepfake detection, we first propose the Fake Speech Wild (FSW) dataset, which includes 254 hours of real and deepfake audio from four different media platforms, focusing on social media. As CMs, we establish a benchmark using public datasets and advanced selfsupervised learning (SSL)-based CMs to evaluate current CMs in real-world scenarios. We also assess the effectiveness of data augmentation strategies in enhancing CM robustness for detecting deepfake speech on social media. Finally, by augmenting public datasets and incorporating the FSW training set, we significantly advanced real-world deepfake audio detection performance, achieving an average equal error rate (EER) of 3.54% across all evaluation sets.