EnvSDD: Benchmarking Environmental Sound Deepfake Detection
This addresses the problem of detecting environmental sound deepfakes for media security and forensics, but it is incremental as it builds on existing detection methods with a new dataset.
The authors tackled the lack of large-scale datasets for detecting deepfakes in environmental sounds by introducing EnvSDD, a curated dataset with 45.25 hours of real and 316.74 hours of fake audio, and proposed a detection system based on a pre-trained audio foundation model that outperforms state-of-the-art systems from speech and singing domains.
Audio generation systems now create very realistic soundscapes that can enhance media production, but also pose potential risks. Several studies have examined deepfakes in speech or singing voice. However, environmental sounds have different characteristics, which may make methods for detecting speech and singing deepfakes less effective for real-world sounds. In addition, existing datasets for environmental sound deepfake detection are limited in scale and audio types. To address this gap, we introduce EnvSDD, the first large-scale curated dataset designed for this task, consisting of 45.25 hours of real and 316.74 hours of fake audio. The test set includes diverse conditions to evaluate the generalizability, such as unseen generation models and unseen datasets. We also propose an audio deepfake detection system, based on a pre-trained audio foundation model. Results on EnvSDD show that our proposed system outperforms the state-of-the-art systems from speech and singing domains.