June 15, 2018
Setting high standards with our new semi-anechoic lab
We are excited to announce the opening of a new state-of-the-art semi-anechoic facility at our Sound Labs in Cambridge, UK. The new lab, which measures 215 cubic meters, sets a high-quality benchmark for testing devices and collecting audio data, supporting our mission to map the world of sounds.
The acoustically insulated lab has been designed and built to our exact specifications, providing anechoic properties when required and enabling us to record real-world audio data that is perfect for machine learning.
“The new lab’s average reverberation time can be counted in milliseconds, and with this performance we can simulate any type of environment and extract data that is suitable for our needs,” says Adrian Stępień, Senior Research Engineer.
Think about what it sounds like when you clap your hands in an unfurnished room versus a furnished room; every room sounds different. The sort of echo, reverberation or deformation of sound is often something we want to remove in order to capture clean sound characteristics.
High-quality, isolated audio data is very important but so too is audio from diverse and relevant environments. Our scientific facilities provide us with the ability to simulate any audio environment with a high degree of precision, which is essential for machine learning.
This focus on quality-in/quality-out is why our market-leading sound recognition software (ai3™) is so precise and accurate.
VP of Data, Dr Moray Grieve added, “When we set out to teach machines to hear it was a zero data challenge. This meant that we had to go out into the world and record everything ourselves because quality is important if you want accuracy. If your algorithms are trained on poor quality data then you can’t deliver the levels of accuracy that consumers expect.
In addition to our in-field data collection campaigns, our state-of-the-art Sound Labs underpin our world-leading position in artificial audio intelligence by enabling us to capture, organise, analyse and model the best quality audio.”
Like this? You can subscribe to our blog and receive an alert every time we publish an announcement, a comment on the industry or something more technical.
About Audio Analytic
Audio Analytic is the pioneer of AI sound recognition software. The company is on a mission to map the world of sounds, offering our sense of hearing to consumer technology. By transferring our sense of hearing to consumer products and digital personal assistants we give them the ability to react to the world around us, helping satisfy our entertainment, safety, security, wellbeing and communication needs.
Audio Analytic’s ai3™ sound recognition software enables device manufacturers and chip companies to equip products with Artificial Audio Intelligence, recognizing and automatically responding to our growing list of sound profiles.