Acoustic event detection kit for power-efficient smart home devices
The Acoustic Event Detection Kit (EVK1) features the company’s analogML core – a fully analog machine learning processor that promotes system power efficiency by identifying specific acoustic events prior to data digitization – along with event detection algorithms and Infineon’s new XENSIV IM73A135 high-performance, low-power analog MEMS microphone. The EVK1 is offered as a complete hardware-software kit for the development of small, always-listening smart home devices with extended battery lifetimes.
Traditional acoustic event detection devices, says the company, are notoriously power-inefficient because they continuously monitor the environment and immediately digitize all microphone data for analysis – even though most of that data are simply noise. A window glass break, for example, may only happen once a decade but the typical glass break sensor uses high-power digital analysis of 100% of the ambient sound data to detect a trigger that rarely (or never) occurs.
The EVK1, on the other hand, says the company, demonstrates a power-saving alternative by using an analogML core to detect acoustic events at the start of the signal chain while the microphone data are still analog, enabling the downstream digital system to remain in an ultra-low-power sleep mode until an event is detected. This architectural approach allows designers to build acoustic event detection devices with batteries that last years, instead of months, on a single charge.
“Stoked by demand for smarter real-time monitoring of potential dangers in the home, the market for acoustic event detection in battery-powered smart home devices is exploding,” says Tom Doyle, founder and CEO, Aspinity. “Such devices help people feel safer and more secure, whether they’re home or away, which is why it’s so important to keep them up and running for extended periods. Our EVK1 makes it easy to develop small devices that can very accurately detect window glass break and run for years, so you can go on vacation knowing that your home will be protected while you’re away – and you’ll be spared those annoying phone calls on false alarms triggered by other loud sounds in the neighborhood.”
EVK1 Features include:
- AnalogML core – a programmable, analog machine learning processor that uses near-zero-power to detect acoustic or other sensor events in analog sensor data
- Infineon’s XENSIV IM73A135 high-performance analog MEMS microphone – a 73 dB SNR analog MEMS microphone with a power consumption of just 170 µA
- Aspinity algorithms – easy to load onto analogML core for acoustic detection of window glass break or voice, with additional acoustic event detection algorithms coming soon
The EVK1 is currently sampling to key customers.
If you enjoyed this article, you will like the following ones: don't miss them by subscribing to :
