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

This paper tackles the problem of verifying the authenticity of speechrecordings from world leaders. Whereas previous work on detecting deep fake ortampered audio focus on scrutinizing an audio recording in isolation, weinstead reframe the problem and focus on cross-verifying a questionablerecording against trusted references. We present a method for cross-verifying aspeech recording against a reference that consists of two steps: aligning thetwo recordings and then classifying each query frame as matching ornon-matching. We propose a subsequence alignment method based on theNeedleman-Wunsch algorithm and show that it significantly outperforms dynamictime warping in handling common tampering operations. We also explore severalbinary classification models based on LSTM and Transformer architectures toverify content at the frame level. Through extensive experiments on tamperedspeech recordings of Donald Trump, we show that our system can reliably detectaudio tampering operations of different types and durations. Our best modelachieves 99.7% accuracy for the alignment task at an error tolerance of 50 msand a 0.43% equal error rate in classifying audio frames as matching ornon-matching.

A Cross-Verification Approach for Protecting World Leaders from Fake and Tampered Audio