Anti-spoofing Methods for Automatic SpeakerVerification System

TL;DR

This paper reviews various acoustic features and classifiers for anti-spoofing in automatic speaker verification, highlighting the effectiveness of magnitude-phase features, wavelet features, and deep neural networks in improving detection robustness.

Contribution

It provides a comprehensive comparison of spoofing detection methods, emphasizing the advantages of combined features and advanced classifiers like DNNs over traditional approaches.

Findings

Magnitude and phase feature combination improves detection accuracy.

Wavelet-based features achieve low equal error rates.

Deep neural networks outperform traditional classifiers in spoofing detection.

Abstract

Growing interest in automatic speaker verification (ASV)systems has lead to significant quality improvement of spoofing attackson them. Many research works confirm that despite the low equal er-ror rate (EER) ASV systems are still vulnerable to spoofing attacks. Inthis work we overview different acoustic feature spaces and classifiersto determine reliable and robust countermeasures against spoofing at-tacks. We compared several spoofing detection systems, presented so far,on the development and evaluation datasets of the Automatic SpeakerVerification Spoofing and Countermeasures (ASVspoof) Challenge 2015.Experimental results presented in this paper demonstrate that the useof magnitude and phase information combination provides a substantialinput into the efficiency of the spoofing detection systems. Also wavelet-based features show impressive results in terms of equal error rate. Inour overview we compare spoofing performance for systems based on dif-ferent classifiers. Comparison results demonstrate that the linear SVMclassifier outperforms the conventional GMM approach. However, manyresearchers inspired by the great success of deep neural networks (DNN)approaches in the automatic speech recognition, applied DNN in thespoofing detection task and obtained quite low EER for known and un-known type of spoofing attacks.