English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Diffusion models have gained prominence in the image domain for theircapabilities in data generation and transformation, achieving state-of-the-artperformance in various tasks in both image and audio domains. In the rapidlyevolving field of audio-based machine learning, safeguarding model integrityand establishing data copyright are of paramount importance. This paperpresents the first watermarking technique applied to audio diffusion modelstrained on mel-spectrograms. This offers a novel approach to the aforementionedchallenges. Our model excels not only in benign audio generation, but alsoincorporates an invisible watermarking trigger mechanism for modelverification. This watermark trigger serves as a protective layer, enabling theidentification of model ownership and ensuring its integrity. Through extensiveexperiments, we demonstrate that invisible watermark triggers can effectivelyprotect against unauthorized modifications while maintaining high utility inbenign audio generation tasks.

Invisible Watermarking for Audio Generation Diffusion Models