Skip to content

The Colin Cherry Laboratory

In a world where the desire – and the need – to interact with computer-based systems is a daily-life experience, machine learning has a crucial role in maximizing the accessibility and functional effectiveness of advanced systems. We foresee the increasing importance of augmented reality (AR) as a way to tap into human perception in a wide range of applications, from healthcare to entertainment to defence. We foresee ‘hearing aids’ evolving into ‘assistive hearing devices for all’. We foresee AR-enabled glasses and acoustically transparent spatial sound rendering. We foresee acoustic scene analysis and synthesis leading to a new generation of audio enhancement technologies.

The voice and audio capabilities of such AR systems, together with audio-visual fusion, currently present many technical challenges in analysis and rendering. Such challenges need to be solved to reach the next level of effectiveness. Our research aims to overcome key components of the AR technical challenges using machine learning techniques in a multidisciplinary research mindset. 

Led by Professor Patrick Naylor, Dr Lorenzo Picinali and Dr Dan Goodman

Our research