# Optimizing Tandem Speaker Verification and Anti-Spoofing Systems

arXiv: https://arxiv.org/abs/2201.09709 · HTML: https://mlsanity.com/paper/2201.09709/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 24 Jan 2022.

## Builds on (most cited first, 21 of 21)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection](https://mlsanity.com/paper/1904.05441/) (2019)
- [ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection](https://mlsanity.com/paper/2109.00537/) (2021)
- [A Comparative Study on Recent Neural Spoofing Countermeasures for Synthetic Speech Detection](https://mlsanity.com/paper/2103.11326/) (2021)
- [BUT System Description to VoxCeleb Speaker Recognition Challenge 2019](https://mlsanity.com/paper/1910.12592/) (2019)
- [STC Antispoofing Systems for the ASVspoof2019 Challenge](https://mlsanity.com/paper/1904.05576/) (2019)
- [Speech is Silver, Silence is Golden: What do ASVspoof-trained Models Really Learn?](https://mlsanity.com/paper/2106.12914/) (2021)
- [Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification: Fundamentals](https://mlsanity.com/paper/2007.05979/) (2020)
- [t-DCF: a Detection Cost Function for the Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification](https://mlsanity.com/paper/1804.09618/) (2018)
- [A Speaker Verification Backend with Robust Performance across Conditions](https://mlsanity.com/paper/2102.01760/) (2021)
- [A comparison of linear and non-linear calibrations for speaker recognition](https://mlsanity.com/paper/1402.2447/) (2014)
- [NPLDA: A Deep Neural PLDA Model for Speaker Verification](https://mlsanity.com/paper/2002.03562/) (2020)
- [Reinforcement Based Learning on Classification Task Could Yield Better Generalization and Adversarial Accuracy](https://mlsanity.com/paper/2012.04353/) (2020)
- [An initial investigation on optimizing tandem speaker verification and countermeasure systems using reinforcement learning](https://mlsanity.com/paper/2002.03801/) (2020)

## Built on by (most cited first, 1 of 1)

- [FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning](https://mlsanity.com/paper/2504.15663/) (2025)

## Abstract (arXiv)

As automatic speaker verification (ASV) systems are vulnerable to spoofing attacks, they are typically used in conjunction with spoofing countermeasure (CM) systems to improve security. For example, the CM can first determine whether the input is human speech, then the ASV can determine whether this speech matches the speaker's identity. The performance of such a tandem system can be measured with a tandem detection cost function (t-DCF). However, ASV and CM systems are usually trained separately, using different metrics and data, which does not optimize their combined performance. In this work, we propose to optimize the tandem system directly by creating a differentiable version of t-DCF and employing techniques from reinforcement learning. The results indicate that these approaches offer better outcomes than finetuning, with our method providing a 20% relative improvement in the t-DCF in the ASVSpoof19 dataset in a constrained setting.