Aspinity, a pioneer in ultra-low-power analog machine learning (AnalogML™) processors, today launched its Voice-First Evaluation Kit (EVK2), a complete hardware/software development kit that demonstrates Aspinity’s ultra-low-power edge processing solution for analog voice activity detection and preroll. The new EVK2 enables customers to easily integrate analog machine learning and analog data compression into battery-operated voice-enabled devices, such as hearables/wearables, smart speakers and smart TV remotes, facilitating significant power savings—without compromising system accuracy.
The EVK2 features the latest generation of Aspinity’s Reconfigurable Analog Modular Processor (RAMP™) chip. As the world’s first implementation of compact, ultra-low power analogML, the RAMP chip introduces a new architectural approach to system design that improves battery life in edge devices. In contrast to alternative always-listening system architectures—which digitize all sound data, relevant or not, before wake word analysis—the RAMP chip uses near-zero power to analyze raw, unstructured analog microphone data at the start of the signal chain to determine if voice is present prior to triggering the wake word engine. Since up to 90% of the sound data captured within a day is not voice, the RAMP chip’s analyze-first approach minimizes the power-on time of the analog-to-digital converter (ADC) and wake word engine (WWE), increasing battery life by up to 10x. The RAMP chip is also the first analog voice wake up solution to continuously collect and compress (into ~2kB of memory) the 500ms of sound prior to the wake word (preroll) that is required by most WWEs in order to accurately determine that a command has been spoken.
The Voice-First EVK2 features:
- The latest-generation RAMP chip, along with voice activity detection and preroll collection, compression, and reconstruction algorithms, a one-source solution for high-accuracy, low-power always-on voice wake up
- Audio test files for quick start-up, and a live audio testing option that uses a high-performance MEMS microphone from Infineon for flexible testing
- Integration with the popular high-performance STM32H743ZI MCU from STMicroelectronics allows the testing of analog voice activity detection with or without preroll collection and delivery to a third-party WWE
“The EVK2 jumpstarts the integration of the RAMP chip into power-efficient voice-enabled devices,” said Tom Doyle, CEO and founder, Aspinity. “For the first time, device designers can realize all of the benefits of analogML and analog compression ― 10x power savings without a reduction in wake word detection accuracy ― for their next generation of voice enabled devices.”