MOS-FAD: Improving Fake Audio Detection Via Automatic Mean Opinion Score Prediction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914652253847552 |
|---|---|
| author | Zhou, Wangjin Yang, Zhengdong Chu, Chenhui Li, Sheng Dabre, Raj Zhao, Yi Kawahara, Tatsuya |
| author_facet | Zhou, Wangjin Yang, Zhengdong Chu, Chenhui Li, Sheng Dabre, Raj Zhao, Yi Kawahara, Tatsuya |
| contents | Automatic Mean Opinion Score (MOS) prediction is employed to evaluate the quality of synthetic speech. This study extends the application of predicted MOS to the task of Fake Audio Detection (FAD), as we expect that MOS can be used to assess how close synthesized speech is to the natural human voice. We propose MOS-FAD, where MOS can be leveraged at two key points in FAD: training data selection and model fusion. In training data selection, we demonstrate that MOS enables effective filtering of samples from unbalanced datasets. In the model fusion, our results demonstrate that incorporating MOS as a gating mechanism in FAD model fusion enhances overall performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_13249 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MOS-FAD: Improving Fake Audio Detection Via Automatic Mean Opinion Score Prediction Zhou, Wangjin Yang, Zhengdong Chu, Chenhui Li, Sheng Dabre, Raj Zhao, Yi Kawahara, Tatsuya Audio and Speech Processing Multimedia Automatic Mean Opinion Score (MOS) prediction is employed to evaluate the quality of synthetic speech. This study extends the application of predicted MOS to the task of Fake Audio Detection (FAD), as we expect that MOS can be used to assess how close synthesized speech is to the natural human voice. We propose MOS-FAD, where MOS can be leveraged at two key points in FAD: training data selection and model fusion. In training data selection, we demonstrate that MOS enables effective filtering of samples from unbalanced datasets. In the model fusion, our results demonstrate that incorporating MOS as a gating mechanism in FAD model fusion enhances overall performance. |
| title | MOS-FAD: Improving Fake Audio Detection Via Automatic Mean Opinion Score Prediction |
| topic | Audio and Speech Processing Multimedia |
| url | https://arxiv.org/abs/2401.13249 |