Skip to yearly menu bar Skip to main content


Poster

Proactive Detection of Voice Cloning with Localized Watermarking

Robin San Roman · Pierre Fernandez · Hady Elsahar · Alexandre Defossez · Teddy Furon · Tuan Tran

Hall C 4-9 #2301
[ ] [ Paper PDF ]
[ Poster
Thu 25 Jul 2:30 a.m. PDT — 4 a.m. PDT

Abstract:

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 https://github.com/facebookresearch/audioseal

Chat is not available.