Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 12 of 12 for “"Voice Biometrics"”.
-
Spoofing Detection in Voice Biometrics: Cochlear Modelling and Perceptually Motivated Features
The automatic speaker verification (ASV) system is one of the most widely adopted biometric technology. However, ASV is vulnerable to spoofing attacks that can significantly affect its reliability. Among the different variants of spoofing attacks, replay attacks pose a major threat as they do not …
-
Replay detection in voice biometrics: an investigation of adaptive and non-adaptive front-ends
Among various physiological and behavioural traits, speech has gained popularity as an effective mode of biometric authentication. Even though they are gaining popularity, automatic speaker verification systems are vulnerable to malicious attacks, known as spoofing attacks. Among various types of …
-
Assessing the Impact of Codec-Induced Audio Degradation on Voice Biometric Systems
This study examines the robustness of voice biometrics when speech signals undergo audio codec transformations and sampling rate variations, conditions common in telecommunication networks. Speaker verification systems such as ECAPA-TDNN perform well on clean datasets, but their accuracy declines …
-
Achieving non-transferability in a digital identity management system
… how non-transferability can be achieved through biometrics. By tying the physical identity of a user to their digital identity, we are better able to prevent users from sharing their credentials. Additionally, we implement a state of the art biometric key generation algorithm and apply it to …
-
Modelling and mitigating the threats to audio based computer systems: experimentation into the use of digital and audio steganography for authentication
… the way we interact with computing devices. Voice assistants have become ubiquitous and are embedded in phones, laptops, cars, smart speakers, and everyday household appliances. The use of speech interfaces has delivered increased convenience and accessibility. Whilst use of voice computing …
-
Elusive Metrics: Quantifying Security of Behavioural Biometrics Against Adversarial Attacks
Behavioural biometrics is gaining popularity as the interaction with smartphones and other smart technologies increases. Behaviour biometrics, such as voice or how a person types, are used to authenticate users through binary classification using machine learning classifiers. Our research …
-
Security-Oriented Voice Authentication Using Machine Learning
… a machine learning and deep learning-based voice authentication system for secure identity verification. As traditional authentication methods such as passwords, PINs, and security tokens continue to face challenges, including identity theft, forgetting, and unauthorized access, voice …
-
A Voice-Based Biometric Watermarking Scheme For Digital Rights Management of 3D Mesh Models
… the identity of the consumer in the form of a voice print, into the graphic content. This voice print serves as a watermark and is created by using a statistical model (Gaussian Mixture Model) representation of the consumer's voice sample. Mel-frequency cepstral coefficients, representing …
-
Access Controls for IIOT Work Systems – Biometric Mechanisms
… iris, ear, gait, palmprint, fingerprint, and voice biometrics within a deep learning-based fusion architecture capable of improving authentication robustness under dynamic operational conditions. To strengthen biometric template security, the framework incorporates biometric watermarking to …
-
Použitelnost Deepfakes v oblasti kybernetické bezpečnosti
Deepfake technológia je v poslednej dobe na vzostupe. Vzniká mnoho techník a nástrojov pre tvorbu deepfake médií a začínajú sa používať ako pre nezákonné tak aj pre prospešné činnosti. Nezákonné použitie vedie k výskumu techník pre detekciu deepfake médií a ich neustálemu zlepšovaniu, takisto ako k …
-
Spoofing Countermeasures for Voice Biometric System: Feature Extraction, Modelling and Compensation
… attacks such as replay, speech synthesis and voice conversion. The main goal of this thesis is to develop dedicated countermeasures to protect ASV systems against spoofing attacks and to make them more secure and robust. This thesis explores an independent modelling framework of high and low …
-
Odolnost biometrické autentizace hlasových asistentů oproti deepfakes
S rozvojom technológie deepfake sa napodobňovanie hlasu cudzích ľudí stalo oveľa jednoduchším. Na napodobnenie hlasu osoby a prípadné oklamanie človeka alebo stroja už nie je potrebné mať profesionálneho imitátora. Útočníkom stačí niekoľko nahrávok hlasu osoby bez ohľadu na obsah, aby vytvorili …