Research project

TAS Hub: Understanding Trust of Perceived Voice Anonymization

Project overview

We investigate why some voices are easy or difficult to anonymize, and how this contributes to attitudes of trust toward voice anonymization systems. The mechanisms at work between algorithmic measurements of anonymity (objective metrics) and human perception of anonymity (subjective metrics) are not well understood. Different adversarial scenarios may require optimizing for objective metrics (e.g., attacks on automatic speaker verification systems) while other scenarios require optimizing for subjective metrics (e.g., human eavesdroppers). The problem of achieving trustworthy anonymization capabilities becomes especially difficult because it is not clear what the ground truth should be.

Staff

Lead researchers

Dr Jennifer Williams

Lecturer

Research interests

  • Responsible and trustworthy audio processing applied to a variety of domains and use-cases;
  • Audio AI safety in terms of usability, privacy, and security;
  • Ethical issues of trust for audio AI (deepfake detection, voice-related rights, and speaker and content privacy). 
Connect with Jennifer

Collaborating research institutes, centres and groups

Research outputs