We use cookies to help us to improve our site and enables us to deliver the best possible service and customer experience. By clicking accept or continuing to use this site you are agreeing to let us share your data with third parties in accordance with our privacy policy. Learn more

News

Receiving you loud and clear – new technology for truly smart TVs

Jan 7, 2020

The new generation of voice-activated smart TVs offers the possibility of never again having to hunt for the remote control down the back of the sofa. But there’s a catch – if your TV can’t hear what you’re saying, you’ll only be replacing one frustration with another.

Shouting at the TV when your football team misses a goal is one thing. But you don’t want to be shouting at it every time you need to change the channel or adjust the volume. But it’s a complex challenge – you’ll be talking to the TV at the same time as it’s talking to you, you’ll be some distance away across the room, and the rest of the family are likely to be chatting to each other at the same time.

Our unique solution uses a statistical approach to solve the problem. It’s autofocus for sound – an ‘acoustic lens’ that enables your smart TV to focus on what you are saying, despite the background noise.

Our data-driven blind audio signal separation technology is able to ‘listen’ to a real-world acoustic scene and identify the prominent sources of sound, including echoes and reflections. Sophisticated algorithms enable it to cancel out the unwanted interference that often makes effective speech recognition impossible.

The system is also adaptive – so any new background noises that appear are also eliminated in real time. And the algorithm has a latency of just five milliseconds – making it ideal for real-time applications like smart TVs.

We've been working with an industry partner to develop the technology and we're seeing some great results from real-world testing. What's more, the code is production ready. So, if you're looking to beat the Amazon Fire TV Cube on performance in noisy environments, we can help.

Our technology is available on a licensing basis to run on standard Arm and Intel platforms. The solution doesn’t need calibrating or training – so existing devices can be easily reconfigured with a software update.

You can hear the difference for yourself at the CES tech show in Las Vegas this week. We'll be doing demonstrations throughout the event (7-10 January) on stand 51902/E at Sands Expo, Hall G.