Codec-Based Deepfake Source Tracing via Neural Audio Codec Taxonomy
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913970839879680 |
|---|---|
| author | Chen, Xuanjun Lin, I-Ming Zhang, Lin Du, Jiawei Wu, Haibin Lee, Hung-yi Jang, Jyh-Shing Roger |
| author_facet | Chen, Xuanjun Lin, I-Ming Zhang, Lin Du, Jiawei Wu, Haibin Lee, Hung-yi Jang, Jyh-Shing Roger |
| contents | Recent advances in neural audio codec-based speech generation (CoSG) models have produced remarkably realistic audio deepfakes. We refer to deepfake speech generated by CoSG systems as codec-based deepfake, or CodecFake. Although existing anti-spoofing research on CodecFake predominantly focuses on verifying the authenticity of audio samples, almost no attention was given to tracing the CoSG used in generating these deepfakes. In CodecFake generation, processes such as speech-to-unit encoding, discrete unit modeling, and unit-to-speech decoding are fundamentally based on neural audio codecs. Motivated by this, we introduce source tracing for CodecFake via neural audio codec taxonomy, which dissects neural audio codecs to trace CoSG. Our experimental results on the CodecFake+ dataset provide promising initial evidence for the feasibility of CodecFake source tracing while also highlighting several challenges that warrant further investigation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_12994 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Codec-Based Deepfake Source Tracing via Neural Audio Codec Taxonomy Chen, Xuanjun Lin, I-Ming Zhang, Lin Du, Jiawei Wu, Haibin Lee, Hung-yi Jang, Jyh-Shing Roger Sound Audio and Speech Processing Recent advances in neural audio codec-based speech generation (CoSG) models have produced remarkably realistic audio deepfakes. We refer to deepfake speech generated by CoSG systems as codec-based deepfake, or CodecFake. Although existing anti-spoofing research on CodecFake predominantly focuses on verifying the authenticity of audio samples, almost no attention was given to tracing the CoSG used in generating these deepfakes. In CodecFake generation, processes such as speech-to-unit encoding, discrete unit modeling, and unit-to-speech decoding are fundamentally based on neural audio codecs. Motivated by this, we introduce source tracing for CodecFake via neural audio codec taxonomy, which dissects neural audio codecs to trace CoSG. Our experimental results on the CodecFake+ dataset provide promising initial evidence for the feasibility of CodecFake source tracing while also highlighting several challenges that warrant further investigation. |
| title | Codec-Based Deepfake Source Tracing via Neural Audio Codec Taxonomy |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.12994 |