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

Nowadays, it is common to release audio content to the public. However, withthe rise of voice cloning technology, attackers have the potential to easilyimpersonate a specific person by utilizing his publicly released audio withoutany permission. Therefore, it becomes significant to detect any potentialmisuse of the released audio content and protect its timbre from beingimpersonated. To this end, we introduce a novel concept, "Timbre Watermarking",which embeds watermark information into the target individual's speech,eventually defeating the voice cloning attacks. To ensure the watermark isrobust to the voice cloning model's learning process, we design an end-to-endvoice cloning-resistant detection framework. The core idea of our solution isto embed and extract the watermark in the frequency domain in a temporallyinvariant manner. To acquire generalization across different voice cloningattacks, we modulate their shared process and integrate it into our frameworkas a distortion layer. Experiments demonstrate that the proposed timbrewatermarking can defend against different voice cloning attacks, exhibit strongresistance against various adaptive attacks (e.g., reconstruction-based removalattacks, watermark overwriting attacks), and achieve practicality in real-worldservices such as PaddleSpeech, Voice-Cloning-App, and so-vits-svc. In addition,ablation studies are also conducted to verify the effectiveness of our design.Some audio samples are available athttps://timbrewatermarking.github.io/samples.

Detecting Voice Cloning Attacks via Timbre Watermarking