One-Class Learning with Adaptive Centroid Shift for Audio Deepfake Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916298911383552 |
|---|---|
| author | Kim, Hyun Myung Jang, Kangwook Kim, Hoirin |
| author_facet | Kim, Hyun Myung Jang, Kangwook Kim, Hoirin |
| contents | As speech synthesis systems continue to make remarkable advances in recent years, the importance of robust deepfake detection systems that perform well in unseen systems has grown. In this paper, we propose a novel adaptive centroid shift (ACS) method that updates the centroid representation by continually shifting as the weighted average of bonafide representations. Our approach uses only bonafide samples to define their centroid, which can yield a specialized centroid for one-class learning. Integrating our ACS with one-class learning gathers bonafide representations into a single cluster, forming well-separated embeddings robust to unseen spoofing attacks. Our proposed method achieves an equal error rate (EER) of 2.19% on the ASVspoof 2021 deepfake dataset, outperforming all existing systems. Furthermore, the t-SNE visualization illustrates that our method effectively maps the bonafide embeddings into a single cluster and successfully disentangles the bonafide and spoof classes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_16716 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | One-Class Learning with Adaptive Centroid Shift for Audio Deepfake Detection Kim, Hyun Myung Jang, Kangwook Kim, Hoirin Audio and Speech Processing Cryptography and Security Sound As speech synthesis systems continue to make remarkable advances in recent years, the importance of robust deepfake detection systems that perform well in unseen systems has grown. In this paper, we propose a novel adaptive centroid shift (ACS) method that updates the centroid representation by continually shifting as the weighted average of bonafide representations. Our approach uses only bonafide samples to define their centroid, which can yield a specialized centroid for one-class learning. Integrating our ACS with one-class learning gathers bonafide representations into a single cluster, forming well-separated embeddings robust to unseen spoofing attacks. Our proposed method achieves an equal error rate (EER) of 2.19% on the ASVspoof 2021 deepfake dataset, outperforming all existing systems. Furthermore, the t-SNE visualization illustrates that our method effectively maps the bonafide embeddings into a single cluster and successfully disentangles the bonafide and spoof classes. |
| title | One-Class Learning with Adaptive Centroid Shift for Audio Deepfake Detection |
| topic | Audio and Speech Processing Cryptography and Security Sound |
| url | https://arxiv.org/abs/2406.16716 |