# Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing

arXiv: https://arxiv.org/abs/2406.17246 · HTML: https://mlsanity.com/paper/2406.17246/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Builds on (most cited first, 26 of 26)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (2020)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural Networks](https://mlsanity.com/paper/2102.11600/) (2021)
- [AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks](https://mlsanity.com/paper/2110.01200/) (2021)
- [End-to-end anti-spoofing with RawNet2](https://mlsanity.com/paper/2011.01108/) (2020)
- [ASVspoof 2021: Towards Spoofed and Deepfake Speech Detection in the Wild](https://mlsanity.com/paper/2210.02437/) (2022)
- [Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation](https://mlsanity.com/paper/2202.12233/) (2022)
- [Learning Debiased Representation via Disentangled Feature Augmentation](https://mlsanity.com/paper/2107.01372/) (2021)
- [Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes](https://mlsanity.com/paper/1706.10239/) (2017)
- [RawBoost: A Raw Data Boosting and Augmentation Method applied to Automatic Speaker Verification Anti-Spoofing](https://mlsanity.com/paper/2111.04433/) (2021)
- [One-class Learning Towards Synthetic Voice Spoofing Detection](https://mlsanity.com/paper/2010.13995/) (2020)
- [Speech is Silver, Silence is Golden: What do ASVspoof-trained Models Really Learn?](https://mlsanity.com/paper/2106.12914/) (2021)
- [SelecMix: Debiased Learning by Contradicting-pair Sampling](https://mlsanity.com/paper/2211.02291/) (2022)
- [Continual Learning for Fake Audio Detection](https://mlsanity.com/paper/2104.07286/) (2021)
- [A Study On Data Augmentation In Voice Anti-Spoofing](https://mlsanity.com/paper/2110.10491/) (2021)
- [Can large-scale vocoded spoofed data improve speech spoofing countermeasure with a self-supervised front end?](https://mlsanity.com/paper/2309.06014/) (2023)
- [The Impact of Silence on Speech Anti-Spoofing](https://mlsanity.com/paper/2309.11827/) (2023)
- [Generalization of Spoofing Countermeasures: a Case Study with ASVspoof 2015 and BTAS 2016 Corpora](https://mlsanity.com/paper/1901.08025/) (2019)
- [Multi-Dataset Co-Training with Sharpness-Aware Optimization for Audio Anti-spoofing](https://mlsanity.com/paper/2305.19953/) (2023)
- [Investigating Active-learning-based Training Data Selection for Speech Spoofing Countermeasure](https://mlsanity.com/paper/2203.14553/) (2022)
- [Data Quality as Predictor of Voice Anti-Spoofing Generalization](https://mlsanity.com/paper/2103.14602/) (2021)
- [Replay attack detection with complementary high-resolution information using end-to-end DNN for the ASVspoof 2019 Challenge](https://mlsanity.com/paper/1904.10134/) (2019)
- [Dataset artefacts in anti-spoofing systems: a case study on the ASVspoof 2017 benchmark](https://mlsanity.com/paper/2010.07913/) (2020)
- [Data Augmentation with Signal Companding for Detection of Logical Access Attacks](https://mlsanity.com/paper/2102.06332/) (2021)

## Built on by (most cited first, 2 of 2)

- [AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge](https://mlsanity.com/paper/2408.17352/) (2024)
- [Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems](https://mlsanity.com/paper/2509.09204/) (2025)

## Abstract (arXiv)

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.