Towards Generalized Source Tracing for Codec-Based Deepfake Speech
Abstract
Recent attempts at source tracing for codec-based deepfake speech (CodecFake), generated by neural audio codec-based speech generation (CoSG) models, have exhibited suboptimal performance. However, how to train source tracing models using simulated CoSG data while maintaining strong performance on real CoSG-generated audio remains an open challenge. In this paper, we show that models trained solely on codec-resynthesized data tend to overfit to non-speech regions and struggle to generalize to unseen content. To mitigate these challenges, we introduce the Semantic-Acoustic Source Tracing Network (SASTNet), which jointly leverages Whisper for semantic feature encoding and Wav2vec2 with AudioMAE for acoustic feature encoding. Our proposed SASTNet achieves state-of-the-art performance on the CoSG test set of the CodecFake+ dataset, demonstrating its effectiveness for reliable source tracing.
Cite
@article{arxiv.2506.07294,
title = {Towards Generalized Source Tracing for Codec-Based Deepfake Speech},
author = {Xuanjun Chen and I-Ming Lin and Lin Zhang and Haibin Wu and Hung-yi Lee and Jyh-Shing Roger Jang},
journal= {arXiv preprint arXiv:2506.07294},
year = {2025}
}
Comments
IEEE ASRU 2025