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

Audio Deepfake Detection (ADD) aims to detect the fake audio generated bytext-to-speech (TTS), voice conversion (VC) and replay, etc., which is anemerging topic. Traditionally we take the mono signal as input and focus onrobust feature extraction and effective classifier design. However, thedual-channel stereo information in the audio signal also includes importantcues for deepfake, which has not been studied in the prior work. In this paper,we propose a novel ADD model, termed as M2S-ADD, that attempts to discoveraudio authenticity cues during the mono-to-stereo conversion process. We firstprojects the mono to a stereo signal using a pretrained stereo synthesizer,then employs a dual-branch neural architecture to process the left and rightchannel signals, respectively. In this way, we effectively reveal the artifactsin the fake audio, thus improve the ADD performance. The experiments on theASVspoof2019 database show that M2S-ADD outperforms all baselines that inputmono. We release the source code at \url{https://github.com/AI-S2-Lab/M2S-ADD}.

Betray Oneself: A Novel Audio DeepFake Detection Model via Mono-to-Stereo Conversion