Technical Report of Nomi Team in the Environmental Sound Deepfake Detection Challenge 2026

Download PDF
Open Webpage

Candy Olivia Mawalim, Haotian Zhang, Shogo Okada

Published: 2025, Last Modified: 27 Feb 2026CoRR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: This paper presents our work for the ICASSP 2026 Environmental Sound Deepfake Detection (ESDD) Challenge. The challenge is based on the large-scale EnvSDD dataset that consists of various synthetic environmental sounds. We focus on addressing the complexities of unseen generators and low-resource black-box scenarios by proposing an audio-text cross-attention model. Experiments with individual and combined text-audio models demonstrate competitive EER improvements over the challenge baseline (BEATs+AASIST model).