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

Advancements in AI-synthesized human voices have created a growing threat ofimpersonation and disinformation, making it crucial to develop methods todetect synthetic human voices. This study proposes a new approach toidentifying synthetic human voices by detecting artifacts of vocoders in audiosignals. Most DeepFake audio synthesis models use a neural vocoder, a neuralnetwork that generates waveforms from temporal-frequency representations likemel-spectrograms. By identifying neural vocoder processing in audio, we candetermine if a sample is synthesized. To detect synthetic human voices, weintroduce a multi-task learning framework for a binary-class RawNet2 model thatshares the feature extractor with a vocoder identification module. By treatingvocoder identification as a pretext task, we constrain the feature extractor tofocus on vocoder artifacts and provide discriminative features for the finalbinary classifier. Our experiments show that the improved RawNet2 model basedon vocoder identification achieves high classification performance on thebinary task overall.

AI-Synthesized Voice Detection Using Neural Vocoder Artifacts