PhD in Computing
Imperial College London, October 2019 - July 2023
Working on generative modeling and self-supervised learning on audio-visual speech.
Details
Studied at Imperial College London from October 2019 to July 2023.
Publications
- LiRA: Learning visual speech representations from audio through self-supervision
- End-to-End Video-to-Speech Synthesis using Generative Adversarial Networks
- Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection
- SVTS: Scalable Video-to-Speech Synthesis
- LA-VocE: Low-SNR Audio-visual Speech Enhancement using Neural Vocoders
- Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection
Thesis
My thesis was titled “Leveraging Audio-visual Speech Effectively via Deep Learning”. [PDF]