# A Study On Convolutional Neural Network Based End-To-End Replay Anti-Spoofing

arXiv: https://arxiv.org/abs/1805.09164 · HTML: https://mlsanity.com/paper/1805.09164/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2018.

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

- [Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks](https://mlsanity.com/paper/2107.08803/) (2021)

## Abstract (arXiv)

The second Automatic Speaker Verification Spoofing and Countermeasures challenge (ASVspoof 2017) focused on "replay attack" detection. The best deep-learning systems to compete in ASVspoof 2017 used Convolutional Neural Networks (CNNs) as a feature extractor. In this paper, we study their performance in an end-to-end setting. We find that these architectures show poor generalization in the evaluation dataset, but find a compact architecture that shows good generalization on the development data. We demonstrate that for this dataset it is not easy to obtain a similar level of generalization on both the development and evaluation data. This leads to a variety of open questions about what the differences are in the data; why these are more evident in an end-to-end setting; and how these issues can be overcome by increasing the training data.