EnvSSLAM-FFN: Lightweight Layer-Fused System for ESDD 2026 Challenge
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914217428254720 |
|---|---|
| author | Guo, Xiaoxuan Huang, Hengyan Zhou, Jiayi Sun, Renhe Liu, Jian Cheng, Haonan Ye, Long Zhang, Qin |
| author_facet | Guo, Xiaoxuan Huang, Hengyan Zhou, Jiayi Sun, Renhe Liu, Jian Cheng, Haonan Ye, Long Zhang, Qin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_20369 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EnvSSLAM-FFN: Lightweight Layer-Fused System for ESDD 2026 Challenge Guo, Xiaoxuan Huang, Hengyan Zhou, Jiayi Sun, Renhe Liu, Jian Cheng, Haonan Ye, Long Zhang, Qin Sound Audio and Speech Processing 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. |
| title | EnvSSLAM-FFN: Lightweight Layer-Fused System for ESDD 2026 Challenge |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2512.20369 |