A Study On Convolutional Neural Network Based End-To-End Replay Anti-Spoofing
This work addresses replay anti-spoofing for speaker verification systems, highlighting challenges in generalization and data differences, but it is incremental as it builds on existing CNN methods from the ASVspoof 2017 challenge.
The study investigated the performance of Convolutional Neural Networks (CNNs) in an end-to-end setting for replay attack detection in speaker verification, finding that these architectures showed poor generalization on evaluation data but identified a compact architecture with good generalization on development data.
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.