March 20, 2019
tinyML goes big
Today I’ll be attending the tinyML Summit at Google’s Campus in Sunnyvale, CA. Organised by a committee that includes representatives from Qualcomm, Google, Arm, UC Berkeley, Stanford University, KU Leuven and Cognite Ventures, the event focuses on how the industry can bring “machine learning to the very edge of the physical world”.
The Summit features presentations, posters and demos from companies actively commercialising extremely energy efficient applications that will drive the adoption of AI.
We were invited by the committee to provide a live demonstration of our world-leading sound recognition tech. In particular, we are showcasing our software running on an Ambiq subthreshold power-optimised processor and using an innovative piezoelectric MEMS microphone from Vesper.
During rest periods (when target sounds are not detected), the device used in the demonstration uses just 0.01mA of power. Upon hearing a target sound, the device wakes up within 0.5ms and consumes just 2.2mA of power. As a result, this solution of low-power hardware and highly-efficient software delivers a sense of hearing to battery-powered devices for between 2-5 years.
And because our sound recognition software is so efficient and accurate, it is able to reliably recognise impulsive sounds even with minimal numbers of audio frames lost during wake up.
This combination of optimised ML software and hardware is what will drive the tinyML revolution and it is a privilege to be asked to be part of this event. I’m looking forward to the next two days of talking about how big these technologies and applications could become.
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.
Audio Analytic is the pioneer of artificial audio intelligence, which is empowering a new generation of smart products to hear and react to the sounds around us.