AntiDeepFake: AI for Deep Fake Speech Recognition

TL;DR

This research study proposes a modern artificial intelligence approach to recognize deepfake voice, also known as generative AI cloned synthetic voice, and consists of all main pipelines from data to evaluation in the whole picture.

Abstract

In this research study, we propose a modern artificial intelligence (AI) approach to recognize deepfake voice, also known as generative AI cloned synthetic voice. Our proposed AI technology, called AntiDeepFake, consists of all main pipelines from data to evaluation in the whole picture. We provide experimental results and scores for all our proposed methods. The main source code for our approach is available in the provided link: https://github.com/enkhtogtokh/antideepfake repository.

Figures (5)

• Figure 1: The proposed AntiDeepFake architecture (AntiDeepFake)
• Figure 2: The Main AI Pipelines
• Figure 3: The ROC Curve of CatBoost
• Figure 4: The ROC Curve of XGBoost
• Figure 5: The ROC Curve of TabNet