Not All Deepfakes Are Created Equal: Triaging Audio Forgeries for Robust Deepfake Singer Identification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912715980668928 |
|---|---|
| author | Salvi, Davide Koops, Hendrik Vincent Quinton, Elio |
| author_facet | Salvi, Davide Koops, Hendrik Vincent Quinton, Elio |
| contents | The proliferation of highly realistic singing voice deepfakes presents a significant challenge to protecting artist likeness and content authenticity. Automatic singer identification in vocal deepfakes is a promising avenue for artists and rights holders to defend against unauthorized use of their voice, but remains an open research problem. Based on the premise that the most harmful deepfakes are those of the highest quality, we introduce a two-stage pipeline to identify a singer's vocal likeness. It first employs a discriminator model to filter out low-quality forgeries that fail to accurately reproduce vocal likeness. A subsequent model, trained exclusively on authentic recordings, identifies the singer in the remaining high-quality deepfakes and authentic audio. Experiments show that this system consistently outperforms existing baselines on both authentic and synthetic content. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17474 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Not All Deepfakes Are Created Equal: Triaging Audio Forgeries for Robust Deepfake Singer Identification Salvi, Davide Koops, Hendrik Vincent Quinton, Elio Sound The proliferation of highly realistic singing voice deepfakes presents a significant challenge to protecting artist likeness and content authenticity. Automatic singer identification in vocal deepfakes is a promising avenue for artists and rights holders to defend against unauthorized use of their voice, but remains an open research problem. Based on the premise that the most harmful deepfakes are those of the highest quality, we introduce a two-stage pipeline to identify a singer's vocal likeness. It first employs a discriminator model to filter out low-quality forgeries that fail to accurately reproduce vocal likeness. A subsequent model, trained exclusively on authentic recordings, identifies the singer in the remaining high-quality deepfakes and authentic audio. Experiments show that this system consistently outperforms existing baselines on both authentic and synthetic content. |
| title | Not All Deepfakes Are Created Equal: Triaging Audio Forgeries for Robust Deepfake Singer Identification |
| topic | Sound |
| url | https://arxiv.org/abs/2510.17474 |