Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing
This work addresses bias issues in audio anti-spoofing systems, which is important for improving security in voice authentication, but it is incremental as it builds on prior observations about silence differences.
The paper tackled the problem of bias in audio anti-spoofing detection by analyzing class-wise differences beyond silence, revealing significant disparities in training dynamics between spoof and bonafide classes, which suggests a need for more robust modeling of the bonafide class.
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.