Auditory Perception Based Anti-Spoofing System for Human Age Verification

Anti-spoofing Methods for Automatic Speaker Verification System

Growing interest in automatic speaker verification (ASV) systems has lead to significant quality improvement of spoofing attacks on them. Many research works confirm that despite the low equal error rate (EER) ASV systems are still vulnerable to spoofing attacks. In this work we overview different acoustic feature spaces and classifiers to determine reliable and robust countermeasures against s...

Introducing i-vectors for joint anti-spoofing and speaker verification

Any biometric recognizer is vulnerable to direct spoofing attacks and automatic speaker verification (ASV) is no exception; replay, synthesis and conversion attacks all provoke false acceptances unless countermeasures are used. We focus on voice conversion (VC) attacks. Most existing countermeasures use full knowledge of a particular VC system to detect spoofing. We study a potentially more uni...

Directional Perception in the Human Auditory System

Human perception of auditory direction was tested in the horizontal and mid-sagittal planes. When the auricular funneling and baffling effects are bypassed by extensions of the ear canals, the accuracy of perception worsens significantly. Providing artificial baffling posterior to the extensions of the ear canals improves perception. The accuracy of perception also worsens when the auricular fu...

Spoofing and Anti-Spoofing Measures

Feature Selection Based on CQCCs for Automatic Speaker Verification Spoofing

The ASVspoof 2017 challenge aims to assess spoofing and countermeasures attack detection accuracy for automatic speaker verification. It has been proven that constant Q cepstral coefficients(CQCCs) processes speech in different frequencies with variable resolution and performs much better than traditional features. When coupled with a Gaussian mixture model (GMM), it is an excellently effective...