Academy Award winning pedigree of AudioTelligence, the Cambridge start-up that's raised £3.1m

Its digital technolgy will improve performance of smart speakers and voice-activated devices

Academy Award-winning engineers are behind a Cambridge start-up that has raised £3.1million to overcome the ‘cocktail party problem’.

AudioTelligence has developed the world’s first digital technology capable of splitting voice from loud background noise effectively.

It will help us understand speakers in a noisy environment and improve the performance of the growing plethora of voice-activated devices.

Rather than using high-quality microphones, it deploys a software approach called blind audio signal separation, which uses Bayesian statistics and machine learning to split the soundscape into separate streams. When new sounds such as air-conditioning, fans or equipment noise are introduced, the technology adapts so that these are also eliminated from the sound heard.

AudioTelligence raised its funding from Cambridge Innovation Capital and Cambridge Enterprise.

The company is a spin-out from CEDAR Audio, the oldest company in Cambridge Enterprise’s portfolio. Founded in 1988, it was based on the research of Professor Peter Rayner, who created the Signal Processing and Communications Laboratory at the University of Cambridge.

AudioTelligence CEO Ken Roberts, who was previously CEO of Pulsic Ltd and has held positions at Akya, Undo and Ateeda, said: “Peter’s expertise was called upon in 1985 when the National Sound Archive first considered digitising its collection to preserve its decaying recordings. His research led to the establishment of CEDAR Audio Ltd in Cambridge, to develop the new science of audio restoration and to commercialise it.”

CEDAR now provides high-value products for markets such as film and TV production and broadcasting, as well as law enforcement and security.

“Today, Peter uses a hearing aid and is therefore acutely aware of the difficulties faced by the hearing impaired when different sources of sound are mixed together,” said Ken.

Spotting the potential for new markets, the CEDAR Audio team, headed by Gordon Reid, Dave Betts, Dr Christopher Hicks and Clive Osborn, together with Prof Rayner and Prof Simon Godsill, opted to spin out a new company.

Chief scientific officer Mr Betts saids: “CEDAR is recognised as an industry leader in signal processing. AudioTelligence builds upon this expertise to provide a low-cost option for integration into consumer devices, but this is a very different market, which is why we decided to spin out the company.”

Reading a list of 100 items to an Amazon Echo Dot, it will recognise 84 items under good conditions – but this drops to 22 when a second sound source creates interference.

Using AudioTelligence software to pre-process the sound enables an Echo Dot to recognise 94 items, even with significant background noise.

Andrew Williamson, investment director for CIC, said Cambridge – where Apple, Google and Amazon all have R&D centres to integrate voice technology into their devices – is an ideal location for AudioTelligence.

“The cluster has specialist expertise in voice recognition and signal processing based on decades of research and engineering. The company is very well connected with the university and already has considerable technical and commercial expertise,” he said.

Mr Betts and Dr Hicks won a Technical Achievement Award from the Academy of Motion Pictures Arts and Sciences in 2005 for developing the noise reduction systems used in most major Hollywood movies.

Dr Robert Swann, co-founder of AlphaMosaic, which was sold to Broadcom, is a non-executive director.

Onespacemedia launches website for AudioTelligence

Cambridge-based web design and development agency Onespacemedia, has launched the new brand and website for AudioTelligence.

Lead designer Fani Wong said: “The core concept of the website is to showcase AudioTelligence’s technology in an intuitive and engaging digital format, demonstrating its effectiveness and commercial application to a wide range of industries.

“We will continue to develop and enhance the site as part of a retainer agreement that will enable us to introduce more in-depth information about potential applications. We’re delighted to have built a platform that will help to drive AudioTelligence forward and we look forward to continuing to strengthen its web presence.”

Ken Roberts, CEO of AudioTelligence, added: “Building a high impact brand and associated marketing is a critical first step for any start-up. It was important that our digital media partner had a deep understanding of our company, our technology and the key markets and applications that we’re targeting.

“Onespacemedia’s experience in the technology sector enabled us to create a flexible brand language that can be extended across all of our channels, a website that presents our technology in a clear and engaging fashion, and a content management system that offers the AT team all of the tools needed to manage an evolving digital presence.

“We’re delighted with the brand and website and we’re looking forward to our continued relationship with Onespacemedia as AudioTelligence continues to grow.”

Read more

Chris Mitchell makes a big noise in smart home marketplace with Audio Analytic in Cambridge

Audio Analytic: ‘The Shazam of real-world sounds’