ADD 2022: the First Audio Deep Synthesis Detection Challenge

TL;DR

The paper introduces the first Audio Deep Synthesis Detection Challenge (ADD 2022), addressing real-world scenarios of audio deepfake detection through three distinct tracks and providing insights into recent progress in the field.

Contribution

It presents a comprehensive challenge with datasets, evaluation protocols, and benchmarks for detecting various types of audio deepfakes, filling a gap in real-world scenario testing.

Findings

Advances in detection accuracy across tracks

Effectiveness of different detection methods

Insights into challenges of real-world audio deepfake detection

Abstract

Audio deepfake detection is an emerging topic, which was included in the ASVspoof 2021. However, the recent shared tasks have not covered many real-life and challenging scenarios. The first Audio Deep synthesis Detection challenge (ADD) was motivated to fill in the gap. The ADD 2022 includes three tracks: low-quality fake audio detection (LF), partially fake audio detection (PF) and audio fake game (FG). The LF track focuses on dealing with bona fide and fully fake utterances with various real-world noises etc. The PF track aims to distinguish the partially fake audio from the real. The FG track is a rivalry game, which includes two tasks: an audio generation task and an audio fake detection task. In this paper, we describe the datasets, evaluation metrics, and protocols. We also report major findings that reflect the recent advances in audio deepfake detection tasks.