Environmental Sound Deepfake Detection Challenge: An Overview

TL;DR

This paper introduces EnvSDD, a large-scale dataset for environmental sound deepfake detection, and discusses the results of the associated challenge to advance detection methods against realistic audio forgeries.

Contribution

The paper presents the first large-scale, diverse dataset EnvSDD for environmental sound deepfake detection and launches the ESDD Challenge as a benchmark for future research.

Findings

Challenge results demonstrate improved detection accuracy

Diverse sound categories enhance model robustness

Baseline methods show potential for real-world application

Abstract

Recent progress in audio generation models has made it possible to create highly realistic and immersive soundscapes, which are now widely used in film and virtual-reality-related applications. However, these audio generators also raise concerns about potential misuse, such as producing deceptive audio for fabricated videos or spreading misleading information. Therefore, it is essential to develop effective methods for detecting fake environmental sounds. Existing datasets for environmental sound deepfake detection (ESDD) remain limited in both scale and the diversity of sound categories they cover. To address this gap, we introduced EnvSDD, the first large-scale curated dataset designed for ESDD. Based on EnvSDD, we launched the ESDD Challenge, recognized as one of the ICASSP 2026 Grand Challenges. This paper presents an overview of the ESDD Challenge, including a detailed analysis of the challenge results.