Generalizable Audio Spoofing Detection using Non-Semantic Representations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918132902264832 |
|---|---|
| author | Das, Arnab Kheir, Yassine El Franzreb, Carlos Herzig, Tim Polzehl, Tim Möller, Sebastian |
| author_facet | Das, Arnab Kheir, Yassine El Franzreb, Carlos Herzig, Tim Polzehl, Tim Möller, Sebastian |
| contents | Rapid advancements in generative modeling have made synthetic audio generation easy, making speech-based services vulnerable to spoofing attacks. Consequently, there is a dire need for robust countermeasures more than ever. Existing solutions for deepfake detection are often criticized for lacking generalizability and fail drastically when applied to real-world data. This study proposes a novel method for generalizable spoofing detection leveraging non-semantic universal audio representations. Extensive experiments have been performed to find suitable non-semantic features using TRILL and TRILLsson models. The results indicate that the proposed method achieves comparable performance on the in-domain test set while significantly outperforming state-of-the-art approaches on out-of-domain test sets. Notably, it demonstrates superior generalization on public-domain data, surpassing methods based on hand-crafted features, semantic embeddings, and end-to-end architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00186 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Generalizable Audio Spoofing Detection using Non-Semantic Representations Das, Arnab Kheir, Yassine El Franzreb, Carlos Herzig, Tim Polzehl, Tim Möller, Sebastian Sound Artificial Intelligence Audio and Speech Processing Rapid advancements in generative modeling have made synthetic audio generation easy, making speech-based services vulnerable to spoofing attacks. Consequently, there is a dire need for robust countermeasures more than ever. Existing solutions for deepfake detection are often criticized for lacking generalizability and fail drastically when applied to real-world data. This study proposes a novel method for generalizable spoofing detection leveraging non-semantic universal audio representations. Extensive experiments have been performed to find suitable non-semantic features using TRILL and TRILLsson models. The results indicate that the proposed method achieves comparable performance on the in-domain test set while significantly outperforming state-of-the-art approaches on out-of-domain test sets. Notably, it demonstrates superior generalization on public-domain data, surpassing methods based on hand-crafted features, semantic embeddings, and end-to-end architectures. |
| title | Generalizable Audio Spoofing Detection using Non-Semantic Representations |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2509.00186 |