Davide Berghi

I am a Research Engineer on the AI4ME project at the Centre for Vision, Speech, and Signal Processing (CVSSP) at the University of Surrey. In collaboration with the BBC and Lancaster University, our team is dedicated to developing advanced technologies and production tools that enable personalised media experiences from capture to delivery. 
I completed my PhD at the University of Surrey in 2024. My research focusses on the audio-visual detection and localisation of speech and sound events. 

In 2024, I received the Judges' Award for the DCASE Challenge Task3.
In 2024, I secured second place in the DCASE Challenge Task3 (Track B).
In 2021, I received the IEEE MMSP Best Student Paper award. 

Beyond my research, I have organised the Workshop on Video Understanding and its Applications at BMVC 2024, co-supervised multiple M.Sc and B.Sc students, and served as a reviewer for several journals and conferences.

Outside of work, I like listening to music and playing the guitar.

Research Engineer in Audio-Visual AI

PhD in “Audio-Visual Detection and Localisation of Speech and Sound Events” at the University of Surrey