[PDF][PDF] A review of speech-centric trustworthy machine learning: Privacy, safety, and fairness
Speech-centric machine learning systems have revolutionized a number of leading
industries ranging from transportation and healthcare to education and defense …
industries ranging from transportation and healthcare to education and defense …
Audio-visual biometric recognition and presentation attack detection: A comprehensive survey
Biometric recognition is a trending technology that uses unique characteristics data to
identify or verify/authenticate security applications. Amidst the classically used biometrics …
identify or verify/authenticate security applications. Amidst the classically used biometrics …
Self-supervised learning based domain regularization for mask-wearing speaker verification
Automatic speaker verification (ASV) faces an unprecedented problem due to mask-wearing
speakers, a consequence of COVID-19. Masked speakers unconsciously alter their normal …
speakers, a consequence of COVID-19. Masked speakers unconsciously alter their normal …
Efficient and privacy-preserving speaker recognition for cybertwin-driven 6G
Q Li, X Lin - IEEE Internet of Things Journal, 2021 - ieeexplore.ieee.org
With the introduction of cybertwin, a new approach to represent human or things in the
cyberspace, it is foreseeable that vehicles will be able to offer more and more services in the …
cyberspace, it is foreseeable that vehicles will be able to offer more and more services in the …
Towards end-to-end private automatic speaker recognition
The development of privacy-preserving automatic speaker verification systems has been the
focus of a number of studies with the intent of allowing users to authenticate themselves …
focus of a number of studies with the intent of allowing users to authenticate themselves …
SpeechHide: A hybrid privacy-preserving mechanism for speech content and voiceprint in speech data sharing
Y Hu, R Li, S Wang, F Tao, Z Sun - 2022 7th IEEE International …, 2022 - ieeexplore.ieee.org
With the development of speech technology, huge amounts of speech data generated by
users is collected by speech service providers and may be used for data sharing. However …
users is collected by speech service providers and may be used for data sharing. However …
Privacy-oriented manipulation of speaker representations
Speaker embeddings are ubiquitous, with applications ranging from speaker recognition
and diarization to speech synthesis and voice anonymization. The amount of information …
and diarization to speech synthesis and voice anonymization. The amount of information …
Nomadic: Normalising Maliciously-Secure Distance with Cosine Similarity for Two-Party Biometric Authentication
Computing the distance between two non-normalized vectors x and y, represented by Δ (x,
y) and comparing it to a predefined public threshold τ is an essential functionality used in …
y) and comparing it to a predefined public threshold τ is an essential functionality used in …
Post-quantum secure two-party computation for iris biometric template protection
Thinking about the protection of biometric data, future attacks using a quantum computer call
for adequate resistance of biometric verification systems. Such systems are often deployed …
for adequate resistance of biometric verification systems. Such systems are often deployed …
[PDF][PDF] Privacy-preserving Cosine Similarity Computation with Malicious Security Applied to Biometric Authentication
Computing distance metrics of sensitive data and comparing to a predefined public
threshold in a privacy-preserving way is an indispensable building block for a wide range of …
threshold in a privacy-preserving way is an indispensable building block for a wide range of …