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

Generalisation -- the ability of a model to perform well on unseen data -- iscrucial for building reliable deep fake detectors. However, recent studies haveshown that the current audio deep fake models fall short of this desideratum.In this paper we show that pretrained self-supervised representations followedby a simple logistic regression classifier achieve strong generalisationcapabilities, reducing the equal error rate from 30% to 8% on the newlyintroduced In-the-Wild dataset. Importantly, this approach also producesconsiderably better calibrated models when compared to previous approaches.This means that we can trust our model's predictions more and use these fordownstream tasks, such as uncertainty estimation. In particular, we show thatthe entropy of the estimated probabilities provides a reliable way of rejectinguncertain samples and further improving the accuracy.

Towards generalisable and calibrated synthetic speech detection with self-supervised representations