Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.0
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912033714208768 |
|---|---|
| author | Wang, Zhiyong Fu, Ruibo Wen, Zhengqi Tao, Jianhua Wang, Xiaopeng Xie, Yuankun Qi, Xin Shi, Shuchen Lu, Yi Liu, Yukun Li, Chenxing Liu, Xuefei Li, Guanjun |
| author_facet | Wang, Zhiyong Fu, Ruibo Wen, Zhengqi Tao, Jianhua Wang, Xiaopeng Xie, Yuankun Qi, Xin Shi, Shuchen Lu, Yi Liu, Yukun Li, Chenxing Liu, Xuefei Li, Guanjun |
| contents | Speech synthesis technology has posed a serious threat to speaker verification systems.
Currently, the most effective fake audio detection methods utilize pretrained models, and integrating features from various layers of pretrained model further enhances detection performance.
However, most of the previously proposed fusion methods require fine-tuning the pretrained models, resulting in excessively long training times and hindering model iteration when facing new speech synthesis technology.
To address this issue, this paper proposes a feature fusion method based on the Mixture of Experts, which extracts and integrates features relevant to fake audio detection from layer features, guided by a gating network based on the last layer feature, while freezing the pretrained model.
Experiments conducted on the ASVspoof2019 and ASVspoof2021 datasets demonstrate that the proposed method achieves competitive performance compared to those requiring fine-tuning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_11909 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.0 Wang, Zhiyong Fu, Ruibo Wen, Zhengqi Tao, Jianhua Wang, Xiaopeng Xie, Yuankun Qi, Xin Shi, Shuchen Lu, Yi Liu, Yukun Li, Chenxing Liu, Xuefei Li, Guanjun Sound Audio and Speech Processing Speech synthesis technology has posed a serious threat to speaker verification systems. Currently, the most effective fake audio detection methods utilize pretrained models, and integrating features from various layers of pretrained model further enhances detection performance. However, most of the previously proposed fusion methods require fine-tuning the pretrained models, resulting in excessively long training times and hindering model iteration when facing new speech synthesis technology. To address this issue, this paper proposes a feature fusion method based on the Mixture of Experts, which extracts and integrates features relevant to fake audio detection from layer features, guided by a gating network based on the last layer feature, while freezing the pretrained model. Experiments conducted on the ASVspoof2019 and ASVspoof2021 datasets demonstrate that the proposed method achieves competitive performance compared to those requiring fine-tuning. |
| title | Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.0 |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.11909 |