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

DeepFake Audio, unlike DeepFake images and videos, has been relatively lessexplored from detection perspective, and the solutions which exist for thesynthetic speech classification either use complex networks or dont generalizeto different varieties of synthetic speech obtained using different generativeand optimization-based methods. Through this work, we propose a channel-wiserecalibration of features using attention feature fusion for synthetic speechdetection and compare its performance against different detection methodsincluding End2End models and Resnet-based models on synthetic speech generatedusing Text to Speech and Vocoder systems like WaveNet, WaveRNN, Tactotron, andWaveGlow. We also experiment with Squeeze Excitation (SE) blocks in our Resnetmodels and found that the combination was able to get better performance. Inaddition to the analysis, we also demonstrate that the combination of Linearfrequency cepstral coefficients (LFCC) and Mel Frequency cepstral coefficients(MFCC) using the attentional feature fusion technique creates better inputfeatures representations which can help even simpler models generalize well onsynthetic speech classification tasks. Our models (Resnet based using featurefusion) trained on Fake or Real (FoR) dataset and were able to achieve 95% testaccuracy with the FoR data, and an average of 90% accuracy with samples wegenerated using different generative models after adapting this framework.

Adaptive re-calibration of channel-wise features for Adversarial Audio Classification