Article

Deepfake audio detection and justification with Explainable Artificial Intelligence (XAI)

2023-10-17

Abstract excerpt

<title>Abstract</title> <p>Deepfake audio refers to synthetically generated audio, often used as legal hoaxes to impersonate human voices. This paper generates fake audio from Fake or Real (FoR) dataset using Generative Adversarial Neural Networks (GANs). FoR dataset has the advantage of a diversity of speakers across 195,000 samples. The proposed work analyses the quality of the generated fake data using the Fré...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 6783eefa-f6fa-526e-abba-7361eb847b7a
DOI: 10.21203/rs.3.rs-3444277/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Deepfake audio detection and justification with Explainable Artificial Intelligence (XAI)DOI 10.21203/rs.3.rs-3444277/v1Read

Deepfake audio detection and justication with Explainable Articial IntelligenceSemantic proximity Read

Fake Voice Detection: A Comparative Analysis of Complex-Valued Deep Learning and Transformer Models across Multiple LanguagesSemantic proximity Read

Optimally Configured Generative Adversarial Networks to Distinguish Real and AI- Generated Human FacesSemantic proximity Read

Cycle-consistent Generative Adversarial Networks (CycleGANs) for the Non-Parallel Creation of Fake Voice MediaSemantic proximity Read

A Novel Deepfake Detection Framework using Audio-Video-Textual FeaturesSemantic proximity Read

Application of Speech Recognition Technology Based on Channel Adversarial Training in the Field of Speech Recognition SystemSemantic proximity Read

EnCoNet: An Ensemble-based Synthetic Speech Attribution Scheme with Convolutional Neural NetworksSemantic proximity Read

Speech Emotion Recognition using Data Augmentation Method by Cycle-Generative Adversarial NetworksSemantic proximity Read

Human Detection of AI-Generated Faces and Voices is Not Domain-GeneralSemantic proximity Read

CiwGAN and fiwGAN: Encoding information in acoustic data to model lexical learning with Generative Adversarial NetworksSemantic proximity Read

Use of Explainable Artificial Intelligence for Analyzing and Explaining Intrusion Detection SystemsSemantic proximity Read

Investigation on Automatic Music Generation Using Gan and Lstm NetworksSemantic proximity Read