Intelligent audio & video
Our world-leading AI capability is revolutionizing end-user experiences, business workflows and manufacturing processes. This drives transformational efficiency and productivity gains for our clients.
Our techniques can identify audio and video characteristics with unprecedented speed and accuracy – from real-time classification of musical genres and spoken word themes, to applying super resolution to damaged or low-grade images.
We’re pushing audio and video product design beyond convention, using a ‘standards plus’ approach to create unique and industry-leading technologies, while taking advantage of high-volume silicon.
Building on our extensive experience, we apply novel techniques in wireless AV, sound beamforming, voice activation, wake-on-word and echo cancellation.
Digital audio & signal processing
Digital audio communications play an essential role in the products we develop, such as codecs carrying voice via satellite or high-quality music over Bluetooth links.
We apply signal conditioning to improve signal quality and enhance audio, whilst driving significant power reductions, adding another dimension to algorithm and processing hardware design.
Optimising the silicon
Disruptive audio and Internet of Things (IoT) technologies demand an innovative approach to silicon design. Our Sapphyre digital signal processing core increases performance for audio applications against cost, whilst significantly reducing power consumption and device size.
Our Ecoutez platform is the world's lowest power, flexible IP block for accelerating Voice Activity Detection, requiring just 11µW – about 100th of the power consumed by a modern hearing aid.
Our multi-disciplinary teams have a proven track record of reinventing the possibilities of high-quality audio and video design, time after time.
This includes the world’s lowest-cost internet radio, the world’s first two-way tour-guide radios, pioneering instantly-installed wireless audio descriptions for visually-impaired and hearing-impaired cinema-goers, and a low-cost multi-channel video conferencing system supporting 24 microphones.
Experts in wireless
Reliability is critical for live events, programme making and control systems with spectrum an increasingly scarce and valuable resource. Our experience in wireless technology and standards allows us to meet these challenges head-on.
From developing the world’s first fully digital radio transceiver, to advising regulators on spectrum usage, we offer clients a diverse range of expertise that ensures critical projects are delivered with exceptional results.
We’re proud to have played a key role in the standardisation of Bluetooth, culminating in our spin-out of Cambridge Silicon Radio (CSR), which became the world’s leading supplier of Bluetooth single-chip transceivers.
From bespoke software stacks and processor cores, to innovative radio and antenna design, our expertise offers unprecedented customisation and control to our clients.
Tech, tools & facilities
Head & Torso Simulator
Using high-accuracy median heads and torsos fitted with calibrated standards-compliant ear and mouth simulators, we’re able to measure audio devices that are worn by or interact with people, including wearables, room speakers, microphones and environmental monitoring devices. Specific tools include Brüel & Kjær 4128C HATS, Audio Precision APx525 and analysis software for PESQ, MOS and POLQA.
Satimo Stargate 64
This anechoic radio and antenna test chamber is one of only a handful of facilities in Europe. Within this six-metre cube, we can carry out automated three-dimensional measurement and visualisation of wireless device behaviour and test body-worn technology using body phantoms or real live test subjects. This helps us to understand and optimise real-word RF performance of products such as smart implants (including implanted telemetry), connected drug delivery devices and wearables.
The Digital Greenhouse is our purpose-built AI research facility, specifically designed to discover, develop and test machine learning approaches in a fast, secure environment. The facility features an NVIDIA DGX-1 Deep Learning Supercomputer, a bank of machine learning computers, petabyte local storage and many teraflops of dedicated compute power.
EMC test chamber
Our fully-shielded ETS-Lindgren anechoic test chamber is suitable for a wide range of EMC and RF testing, which is essential for new devices. It allows us to test for unwanted radiation and susceptibility to interference at an early stage with the results fed directly into product design, rather than later on when changes will be expensive to implement.