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

by   Bhusan Chettri, et al.
Queen Mary University of London

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.


page 1

page 2

page 3

page 4


Integrated Replay Spoofing-aware Text-independent Speaker Verification

A number of studies have successfully developed speaker verification or ...

ConvNext Based Neural Network for Anti-Spoofing

Automatic speaker verification (ASV) has been widely used in the real li...

Audio-replay attack detection countermeasures

This paper presents the Speech Technology Center (STC) replay attack det...

Impact of Channel Variation on One-Class Learning for Spoof Detection

The value of Spoofing detection in increasing the reliability of the ASV...

End-to-end spoofing detection with raw waveform CLDNNs

Albeit recent progress in speaker verification generates powerful models...

Verification Code Recognition Based on Active and Deep Learning

A verification code is an automated test method used to distinguish betw...

Attentive Filtering Networks for Audio Replay Attack Detection

An attacker may use a variety of techniques to fool an automatic speaker...

Please sign up or login with your details

Forgot password? Click here to reset