Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929473766555648 |
|---|---|
| author | Shim, Hye-jin Sahidullah, Md Jung, Jee-weon Watanabe, Shinji Kinnunen, Tomi |
| author_facet | Shim, Hye-jin Sahidullah, Md Jung, Jee-weon Watanabe, Shinji Kinnunen, Tomi |
| contents | Current trends in audio anti-spoofing detection research strive to improve models' ability to generalize across unseen attacks by learning to identify a variety of spoofing artifacts. This emphasis has primarily focused on the spoof class. Recently, several studies have noted that the distribution of silence differs between the two classes, which can serve as a shortcut. In this paper, we extend class-wise interpretations beyond silence. We employ loss analysis and asymmetric methodologies to move away from traditional attack-focused and result-oriented evaluations towards a deeper examination of model behaviors. Our investigations highlight the significant differences in training dynamics between the two classes, emphasizing the need for future research to focus on robust modeling of the bonafide class. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_17246 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing Shim, Hye-jin Sahidullah, Md Jung, Jee-weon Watanabe, Shinji Kinnunen, Tomi Sound Artificial Intelligence Audio and Speech Processing Current trends in audio anti-spoofing detection research strive to improve models' ability to generalize across unseen attacks by learning to identify a variety of spoofing artifacts. This emphasis has primarily focused on the spoof class. Recently, several studies have noted that the distribution of silence differs between the two classes, which can serve as a shortcut. In this paper, we extend class-wise interpretations beyond silence. We employ loss analysis and asymmetric methodologies to move away from traditional attack-focused and result-oriented evaluations towards a deeper examination of model behaviors. Our investigations highlight the significant differences in training dynamics between the two classes, emphasizing the need for future research to focus on robust modeling of the bonafide class. |
| title | Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.17246 |