# Multi-Dataset Co-Training with Sharpness-Aware Optimization for Audio Anti-spoofing

arXiv: https://arxiv.org/abs/2305.19953 · HTML: https://mlsanity.com/paper/2305.19953/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 47 references that are in the map.
- First posted on arXiv 31 May 2023.

## Builds on (most cited first, 30 of 33)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Sharpness-Aware Minimization for Efficiently Improving Generalization](https://mlsanity.com/paper/2010.01412/) (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)
- [ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection](https://mlsanity.com/paper/1904.05441/) (2019)
- [Towards Understanding Sharpness-Aware Minimization](https://mlsanity.com/paper/2206.06232/) (2022)
- [Towards Efficient and Scalable Sharpness-Aware Minimization](https://mlsanity.com/paper/2203.02714/) (2022)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation](https://mlsanity.com/paper/2202.12233/) (2022)
- [Sharpness-Aware Minimization Improves Language Model Generalization](https://mlsanity.com/paper/2110.08529/) (2021)
- [Improving Generalization in Federated Learning by Seeking Flat Minima](https://mlsanity.com/paper/2203.11834/) (2022)
- [WaveFake: A Data Set to Facilitate Audio Deepfake Detection](https://mlsanity.com/paper/2111.02813/) (2021)
- [Voice Conversion Challenge 2020: Intra-lingual semi-parallel and cross-lingual voice conversion](https://mlsanity.com/paper/2008.12527/) (2020)
- [End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection](https://mlsanity.com/paper/2107.12710/) (2021)
- [The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods](https://mlsanity.com/paper/1804.04262/) (2018)
- [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)
- [JSUT corpus: free large-scale Japanese speech corpus for end-to-end speech synthesis](https://mlsanity.com/paper/1711.00354/) (2017)
- [Replay and Synthetic Speech Detection with Res2net Architecture](https://mlsanity.com/paper/2010.15006/) (2020)
- [Do We Need More Training Data?](https://mlsanity.com/paper/1503.01508/) (2015)
- [Continual Learning for Fake Audio Detection](https://mlsanity.com/paper/2104.07286/) (2021)
- [ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks](https://mlsanity.com/paper/1904.01120/) (2019)
- [Training of Convolutional Networks on Multiple Heterogeneous Datasets for Street Scene Semantic Segmentation](https://mlsanity.com/paper/1803.05675/) (2018)
- [A Study On Data Augmentation In Voice Anti-Spoofing](https://mlsanity.com/paper/2110.10491/) (2021)
- [An Empirical Study on Channel Effects for Synthetic Voice Spoofing Countermeasure Systems](https://mlsanity.com/paper/2104.01320/) (2021)
- [Multi-dataset Training of Transformers for Robust Action Recognition](https://mlsanity.com/paper/2209.12362/) (2022)
- [Generalization of Spoofing Countermeasures: a Case Study with ASVspoof 2015 and BTAS 2016 Corpora](https://mlsanity.com/paper/1901.08025/) (2019)
- [Investigating Active-learning-based Training Data Selection for Speech Spoofing Countermeasure](https://mlsanity.com/paper/2203.14553/) (2022)

## Built on by (most cited first, 9 of 9)

- [The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio](https://mlsanity.com/paper/2405.04880/) (2024)
- [Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes](https://mlsanity.com/paper/2412.13573/) (2024)
- [Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset](https://mlsanity.com/paper/2410.09869/) (2024)
- [SZU-AFS Antispoofing System for the ASVspoof 5 Challenge](https://mlsanity.com/paper/2408.09933/) (2024)
- [Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey](https://mlsanity.com/paper/2411.17911/) (2024)
- [Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems](https://mlsanity.com/paper/2509.09204/) (2025)
- [Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing](https://mlsanity.com/paper/2406.17246/) (2024)
- [AMA-SAM: Adversarial Multi-Domain Alignment of Segment Anything Model for High-Fidelity Histology Nuclei Segmentation](https://mlsanity.com/paper/2503.21695/) (2025)
- [FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning](https://mlsanity.com/paper/2504.15663/) (2025)

## Abstract (arXiv)

Audio anti-spoofing for automatic speaker verification aims to safeguard users' identities from spoofing attacks. Although state-of-the-art spoofing countermeasure(CM) models perform well on specific datasets, they lack generalization when evaluated with different datasets. To address this limitation, previous studies have explored large pre-trained models, which require significant resources and time. We aim to develop a compact but well-generalizing CM model that can compete with large pre-trained models. Our approach involves multi-dataset co-training and sharpness-aware minimization, which has not been investigated in this domain. Extensive experiments reveal that proposed method yield competitive results across various datasets while utilizing 4,000 times less parameters than the large pre-trained models.