Proactive Detection of Voice Cloning with Localized Watermarking - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Proactive Detection of Voice Cloning with Localized Watermarking

Résumé

In the rapidly evolving field of speech generative models, there is a pressing need to ensure audio authenticity against the risks of voice cloning. We present AudioSeal, the first audio watermarking technique designed specifically for localized detection of AI-generated speech. AudioSeal employs a generator / detector architecture trained jointly with a localization loss to enable localized watermark detection up to the sample level, and a novel perceptual loss inspired by auditory masking, that enables AudioSeal to achieve better imperceptibility. AudioSeal achieves state-of-the-art performance in terms of robustness to real life audio manipulations and imperceptibility based on automatic and human evaluation metrics. Additionally, AudioSeal is designed with a fast, single-pass detector, that significantly surpasses existing models in speed, achieving detection up to two orders of magnitude faster, making it ideal for large-scale and real-time applications. Code is available at \href{https://github.com/facebookresearch/audioseal}{github.com/facebookresearch/audioseal}.

Mots clés

Fichier principal
Vignette du fichier
AudioWatermarking-2.pdf (763.91 Ko) Télécharger le fichier
Origine Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-04610152 , version 1 (12-06-2024)

Licence

Identifiants

  • HAL Id : hal-04610152 , version 1

Citer

Robin San Roman, Pierre Fernandez, Hady Elsahar, Alexandre Défossez, Teddy Furon, et al.. Proactive Detection of Voice Cloning with Localized Watermarking. ICML 2024 - 41st International Conference on Machine Learning, PMLR, Jul 2024, Vienna, Austria. pp.1-17. ⟨hal-04610152⟩
0 Consultations
0 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More