Robust Audio Anti-Spoofing with Fusion-Reconstruction Learning on Multi-Order Spectrograms
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916420996038656 |
|---|---|
| author | Wen, Penghui Hu, Kun Yue, Wenxi Zhang, Sen Zhou, Wanlei Wang, Zhiyong |
| author_facet | Wen, Penghui Hu, Kun Yue, Wenxi Zhang, Sen Zhou, Wanlei Wang, Zhiyong |
| contents | Robust audio anti-spoofing has been increasingly challenging due to the recent advancements on deepfake techniques. While spectrograms have demonstrated their capability for anti-spoofing, complementary information presented in multi-order spectral patterns have not been well explored, which limits their effectiveness for varying spoofing attacks. Therefore, we propose a novel deep learning method with a spectral fusion-reconstruction strategy, namely S2pecNet, to utilise multi-order spectral patterns for robust audio anti-spoofing representations. Specifically, spectral patterns up to second-order are fused in a coarse-to-fine manner and two branches are designed for the fine-level fusion from the spectral and temporal contexts. A reconstruction from the fused representation to the input spectrograms further reduces the potential fused information loss. Our method achieved the state-of-the-art performance with an EER of 0.77% on a widely used dataset: ASVspoof2019 LA Challenge. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_09302 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Robust Audio Anti-Spoofing with Fusion-Reconstruction Learning on Multi-Order Spectrograms Wen, Penghui Hu, Kun Yue, Wenxi Zhang, Sen Zhou, Wanlei Wang, Zhiyong Sound Artificial Intelligence Multimedia Audio and Speech Processing Robust audio anti-spoofing has been increasingly challenging due to the recent advancements on deepfake techniques. While spectrograms have demonstrated their capability for anti-spoofing, complementary information presented in multi-order spectral patterns have not been well explored, which limits their effectiveness for varying spoofing attacks. Therefore, we propose a novel deep learning method with a spectral fusion-reconstruction strategy, namely S2pecNet, to utilise multi-order spectral patterns for robust audio anti-spoofing representations. Specifically, spectral patterns up to second-order are fused in a coarse-to-fine manner and two branches are designed for the fine-level fusion from the spectral and temporal contexts. A reconstruction from the fused representation to the input spectrograms further reduces the potential fused information loss. Our method achieved the state-of-the-art performance with an EER of 0.77% on a widely used dataset: ASVspoof2019 LA Challenge. |
| title | Robust Audio Anti-Spoofing with Fusion-Reconstruction Learning on Multi-Order Spectrograms |
| topic | Sound Artificial Intelligence Multimedia Audio and Speech Processing |
| url | https://arxiv.org/abs/2308.09302 |