ArtificialPersona
Published:
Team project at Queen’s University (with Ovil Miranda, Carter Moore, Zane Prance, Kanika Poonia, Faiz Farook, and Safowan Mostaque) demonstrating real-time anonymisation across both audio and video channels. The pipeline chains:
- Speech-to-text transcribes incoming audio.
- Text-to-speech synthesises the transcript in a different voice profile.
- Deepfake swaps the user’s face for a synthetic persona in the video feed.
The goal: show that high-fidelity end-to-end anonymisation of online communication is feasible with off-the-shelf neural networks running close to real time.