# EnvSSLAM-FFN: Lightweight Layer-Fused System for ESDD 2026 Challenge

arXiv: https://arxiv.org/abs/2512.20369 · HTML: https://mlsanity.com/paper/2512.20369/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Dec 2025.

## Built on by (most cited first, 2 of 2)

- [Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learning](https://mlsanity.com/paper/2601.02983/) (2026)
- [AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan](https://mlsanity.com/paper/2604.08184/) (2026)

## Abstract (arXiv)

Recent advances in generative audio models have enabled high-fidelity environmental sound synthesis, raising serious concerns for audio security. The ESDD 2026 Challenge therefore addresses environmental sound deepfake detection under unseen generators (Track 1) and black-box low-resource detection (Track 2) conditions. We propose EnvSSLAM-FFN, which integrates a frozen SSLAM self-supervised encoder with a lightweight FFN back-end. To effectively capture spoofing artifacts under severe data imbalance, we fuse intermediate SSLAM representations from layers 4-9 and adopt a class-weighted training objective. Experimental results show that the proposed system consistently outperforms the official baselines on both tracks, achieving Test Equal Error Rates (EERs) of 1.20% and 1.05%, respectively.