ADD 2023: Towards Audio Deepfake Detection and Analysis in the Wild

TL;DR

The ADD 2023 challenge advances audio deepfake detection by addressing real-world scenarios like manipulation localization and source attribution, analyzing top methods, and outlining future research directions.

Contribution

This paper introduces a comprehensive dataset and challenge tasks for audio deepfake detection, emphasizing real-world applications and analyzing top participant methodologies.

Findings

Top methods employ diverse deep learning techniques.

Common challenges include manipulation localization accuracy.

Identified limitations guide future research directions.

Abstract

The growing prominence of the field of audio deepfake detection is driven by its wide range of applications, notably in protecting the public from potential fraud and other malicious activities, prompting the need for greater attention and research in this area. The ADD 2023 challenge goes beyond binary real/fake classification by emulating real-world scenarios, such as the identification of manipulated intervals in partially fake audio and determining the source responsible for generating any fake audio, both with real-life implications, notably in audio forensics, law enforcement, and construction of reliable and trustworthy evidence. To further foster research in this area, in this article, we describe the dataset that was used in the fake game, manipulation region location and deepfake algorithm recognition tracks of the challenge. We also focus on the analysis of the technical methodologies by the top-performing participants in each task and note the commonalities and differences in their approaches. Finally, we discuss the current technical limitations as identified through the technical analysis, and provide a roadmap for future research directions. The dataset is available for download at http://addchallenge.cn/downloadADD2023.