Fellowship to advance sound to new frontiers using AI

The Engineering and Physical Sciences Research Council (EPSRC) has given a prestigious Fellowship Award to the University of Surrey’s Professor Mark Plumbley, who will use it to further improve how machines listen to the world around us.

Professor Plumbley will use his EPSRC Fellowship to transform how AI understands everyday sounds – from our homes, outdoor environments, to the workplace – tackling key issues that have prevented computational analysis of sound from reaching its potential.

The Fellowship will focus on four key areas:

Monitoring sounds of human activity in the home to help with assisted living
Measuring sounds in non-domestic buildings to improve the office and workplace environment
Measuring sounds in smart cities to improve the urban environment
Developing sound tools to help producers and consumers of broadcast creative content

Professor Plumbley is an expert in the detection, analysis and separation of sounds. He founded the influential Detection and Classification of Acoustic Scenes and Events (DCASE) challenge – an annual showcase for researchers to discuss and present their work world-wide.

The Fellowship will be supported by a wide range of partner organisations, including Accenture, Audio Analytic, BBC R&D, the Connected Placed Catapult, the Digital Catapult, the Environment Agency, Pindrop, Samsung, The Alan Turing Institute, and the UK Dementia Research Institute.

Mark Plumbley, Head of School for Computer Science and Electronic Engineering at Surrey and Professor of Signal Processing at the University’s world-leading Centre for Vision Speech and Signal Processing (CVSSP), said: “This new Fellowship will allow us to take the field of computational sound analysis to a new level.

“While products such as smart speakers have brought the idea of AI assisted sound analysis to the wider market, the truth is we are only scratching the surface. Working with an amazing set of partners, we hope our research will allow smart sound sensors to have greater impact on people’s day-to-day lives; from helping the elderly live safer lives to improving productivity in the workplace.”

Professor Adrian Hilton, Director of CVSSP at the University of Surrey, said: “The award of a prestigious EPSRC Fellowship to Prof. Plumbley in AI for Sound is an exciting opportunity to continue the ground-breaking research in natural sound recognition which will underpin future devices and technologies used by us all for healthcare, security and entertainment”.

About CVSSP

The Centre for Vision, Speech and Signal Processing (CVSSP) at the University of Surrey is an International Centre of Excellence for research in Audio-Visual Machine Perception, with 125 researchers, a grant portfolio of £24M (£17.5M EPSRC) and a turnover of £7M/annum.

CVSSP has a compute facility with 120 GPUs for deep learning and >1PB of high-speed secure storage. National standing is evidenced by sustained EPSRC investment, including two Programme Grants (2013-19, 2015-21) and three Platform Grants in Audio-Visual Research (2003-08, 2008-14, 2017-22), and as a lead partner of the BBC Data Science and Audio Research partnerships. CVSSP is part of the Department of Electronic and Electrical Engineering. The centre has an outstanding track record of pioneering research leading to successful technology transfer with UK industry and spin-out companies.

The Fellowship is part of AI@Surrey, an interdisciplinary network of over 300 researchers in artificial intelligence and machine learning across the University of Surrey.