# A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection

arXiv: https://arxiv.org/abs/2103.11326 · HTML: https://mlsanity.com/paper/2103.11326/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Mar 2021.

## Built on by (most cited first, 30 of 56)

- [AASIST: Audio Anti-Spoofing using Integrated Spectro-Temporal Graph Attention Networks](https://mlsanity.com/paper/2110.01200/) (2021)
- [ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection](https://mlsanity.com/paper/2109.00537/) (2021)
- [Does Audio Deepfake Detection Generalize?](https://mlsanity.com/paper/2203.16263/) (2022)
- [SafeEar: Content Privacy-Preserving Audio Deepfake Detection](https://mlsanity.com/paper/2409.09272/) (2024)
- [ASVspoof 2021: Automatic Speaker Verification Spoofing and Countermeasures Challenge Evaluation Plan](https://mlsanity.com/paper/2109.00535/) (2021)
- [Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing](https://mlsanity.com/paper/2504.05657/) (2025)
- [Human Perception of Audio Deepfakes](https://mlsanity.com/paper/2107.09667/) (2021)
- [Partially Fake Audio Detection by Self-attention-based Fake Span Discovery](https://mlsanity.com/paper/2202.06684/) (2022)
- [A Comprehensive Real-World Assessment of Audio Watermarking Algorithms: Will They Survive Neural Codecs?](https://mlsanity.com/paper/2505.19663/) (2025)
- [Deepfake audio detection by speaker verification](https://mlsanity.com/paper/2209.14098/) (2022)
- [How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio?](https://mlsanity.com/paper/2406.02483/) (2024)
- [Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detection](https://mlsanity.com/paper/2206.13979/) (2022)
- [SpecRNet: Towards Faster and More Accessible Audio DeepFake Detection](https://mlsanity.com/paper/2210.06105/) (2022)
- [QFA2SR: Query-Free Adversarial Transfer Attacks to Speaker Recognition Systems](https://mlsanity.com/paper/2305.14097/) (2023)
- [Harder or Different? Understanding Generalization of Audio Deepfake Detection](https://mlsanity.com/paper/2406.03512/) (2024)
- [Coarse-to-Fine Proposal Refinement Framework for Audio Temporal Forgery Detection and Localization](https://mlsanity.com/paper/2407.16554/) (2024)
- [Anti-Spoofing Using Transfer Learning with Variational Information Bottleneck](https://mlsanity.com/paper/2204.01387/) (2022)
- [HM-Conformer: A Conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methods](https://mlsanity.com/paper/2309.08208/) (2023)
- [USTC-KXDIGIT System Description for ASVspoof5 Challenge](https://mlsanity.com/paper/2409.01695/) (2024)
- [Diffuse or Confuse: A Diffusion Deepfake Speech Dataset](https://mlsanity.com/paper/2410.06796/) (2024)
- [Complex-valued neural networks for voice anti-spoofing](https://mlsanity.com/paper/2308.11800/) (2023)
- [Collaborative Watermarking for Adversarial Speech Synthesis](https://mlsanity.com/paper/2309.15224/) (2023)
- [Retrieval-Augmented Audio Deepfake Detection](https://mlsanity.com/paper/2404.13892/) (2024)
- [How to Construct Perfect and Worse-than-Coin-Flip Spoofing Countermeasures: A Word of Warning on Shortcut Learning](https://mlsanity.com/paper/2306.00044/) (2023)
- [Weakly-supervised Audio Temporal Forgery Localization via Progressive Audio-language Co-learning Network](https://mlsanity.com/paper/2505.01880/) (2025)
- [Replay Attacks Against Audio Deepfake Detection](https://mlsanity.com/paper/2505.14862/) (2025)
- [Range-Based Equal Error Rate for Spoof Localization](https://mlsanity.com/paper/2305.17739/) (2023)
- [SZU-AFS Antispoofing System for the ASVspoof 5 Challenge](https://mlsanity.com/paper/2408.09933/) (2024)
- [VoiceWukong: Benchmarking Deepfake Voice Detection](https://mlsanity.com/paper/2409.06348/) (2024)
- [Robust Audio Anti-Spoofing with Fusion-Reconstruction Learning on Multi-Order Spectrograms](https://mlsanity.com/paper/2308.09302/) (2023)

## Abstract (arXiv)

A great deal of recent research effort on speech spoofing countermeasures has been invested into back-end neural networks and training criteria. We contribute to this effort with a comparative perspective in this study. Our comparison of countermeasure models on the ASVspoof 2019 logical access task takes into account recently proposed margin-based training criteria, widely used front ends, and common strategies to deal with varied-length input trials. We also measured intra-model differences through multiple training-evaluation rounds with random initialization. Our statistical analysis demonstrates that the performance of the same model may be significantly different when just changing the random initial seed. Thus, we recommend similar analysis or multiple training-evaluation rounds for further research on the database. Despite the intra-model differences, we observed a few promising techniques such as the average pooling to process varied-length inputs and a new hyper-parameter-free loss function. The two techniques led to the best single model in our experiment, which achieved an equal error rate of 1.92% and was significantly different in statistical sense from most of the other experimental models.