ESDD 2026: Environmental Sound Deepfake Detection Challenge Evaluation Plan
By: Han Yin , Yang Xiao , Rohan Kumar Das and more
Potential Business Impact:
Detects fake sounds in videos and games.
Recent advances in audio generation systems have enabled the creation of highly realistic and immersive soundscapes, which are increasingly used in film and virtual reality. However, these audio generators also raise concerns about potential misuse, such as generating deceptive audio content for fake videos and spreading misleading information. Existing datasets for environmental sound deepfake detection (ESDD) are limited in scale and audio types. To address this gap, we have proposed EnvSDD, the first large-scale curated dataset designed for ESDD, consisting of 45.25 hours of real and 316.7 hours of fake sound. Based on EnvSDD, we are launching the Environmental Sound Deepfake Detection Challenge. Specifically, we present two different tracks: ESDD in Unseen Generators and Black-Box Low-Resource ESDD, covering various challenges encountered in real-life scenarios. The challenge will be held in conjunction with the 2026 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026).
Similar Papers
EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection
Audio and Speech Processing
Stops fake voices from tricking people over the phone.
Descriptor:: Extended-Length Audio Dataset for Synthetic Voice Detection and Speaker Recognition (ELAD-SVDSR)
Audio and Speech Processing
Makes fake voices sound more real.
FakeSound2: A Benchmark for Explainable and Generalizable Deepfake Sound Detection
Sound
Finds fake voices in recordings.