Arpita Saggar
Research Topic: A virtual patient to support medical training.
Supervisors: Prof David Hogg, Prof Vania Dimitrova, Dr Duygu Sarikaya, Dr Jonathan Darling.
About Arpita: Before joining the CDT, I worked with UNICEF Save the Children to predict multi-dimensional child poverty in LMICs, as part of the Data Science for Social Good fellowship, based at the University of Warwick. My background is in Computing, and I hold a BSc Hons in Computer Science and a Master of Computer Applications from the University of Delhi.
Project Description: Current methods to evaluate and develop the clinical competencies of doctors use simulated interactions where actors fulfil patient roles. The focus of this project is to develop interactive video-based patient simulations, which can reduce the costs and administrative overhead associated with employing actors, and help scale up training within the health service. The research will leverage state-of-the-art generative models to produce persona-consistent dialogues, synthesise speech with varied intonation, and generate an expressive talking head avatar.