Ultra-low-power analog voice wake-up IC serves battery-operated devices
Aspinity’s analog edge solution for voice wake-up reduces power of current systems by up to 10x
Automation / Robotics
Aspinity, a pioneer in power-efficient edge intelligence for always-on sensing devices, has demonstrated the world’s most power-efficient end-to-end voice wake-up solutions for voice-first devices. Delivering a post-microphone audio chain that draws as little as 25µA of current when always-listening and collecting preroll data, Aspinity’s front-to-back system combines the latest generation of its Reconfigurable Analog Modular Processor (RAMP) chip with two of STMicroelectronics’ popular microcontrollers (MCUs). Achieving unparalleled power efficiency, this solution clears the path for a new wave of always-on, high-accuracy voice-first devices with extended battery lifetimes.
“From smart speakers and hearables to voice-controlled TV remotes, consumers love using voice to interact with the always-on smart electronic products in their lives,” said Tom Doyle, founder and CEO, Aspinity. “But there’s a serious problem facing system designers today: Legacy system architectures that digitize all the sound data up front are notoriously inefficient, clogging the cloud and wasting battery life on irrelevant data. We designed our RAMP IC to address this power challenge right at the root by enabling a more intelligent, data-efficient, system-level edge architecture.”
Unlike other digital-only solutions using low-power MCUs or DSPs, the RAMP IC is a neuromorphic analog processing chip that designers can drop into the front end of a typical wake word-driven system and immediately improve the system’s efficiency by focusing downstream data processing on the important data. By detecting voice at the earliest point in the signal chain — when the data is still analog — the RAMP IC eliminates the digitization and analysis of irrelevant non-voice data and reduces system power by up to 10x.
Aspinity Voice Wake-Up Solutions
Aspinity has demonstrated its low-power voice-activity detection (VAD) plus preroll solution in combination with two ST MCUs. Combining its RAMP IC with the STM32H7 and the STM32L4, ultra-high performance and power-efficient MCUs for connected and non-connected applications, Aspinity enables “analyze-first” always-listening systems that deliver an order-of-magnitude improvement in battery life for users while maintaining wake word accuracy. Testing these VAD systems with both the Amazon and the Sensory TrulyHandsfree wake word engines (WWE) has shown that the Aspinity preroll compression and reconstruction algorithm does not affect WWE accuracy.
“Voice has become the preferred human-machine interface for device interaction, and we are seeing the voice revolution extend to low-power devices like wearables, hearables, TV remote controls and more,” said Todd Mozer, CEO, Sensory. “Combining Aspinity’s analog voice activity detection and preroll collection with Sensory’s industry-leading TrulyHandsfree voice control algorithms brings a new level of low-power, on-device voice solutions, focusing system processing only on voice. This allows device designers to deliver secure, high-performance and efficient battery-operated voice-first solutions that never send wake words to the cloud.”
While Aspinity is focused primarily on voice-first applications, the Aspinity RAMP chip is highly flexible and programmable, a combination that allows it to support a wide range of applications using MEMS microphones, accelerometers or other sensors. Since launching its RAMP technology in June 2019, Aspinity has collaborated with industry leaders to demonstrate other ultra-low-power event-driven sensing applications such as acoustic event detection for glass break and alarm detection as well as a real-time vibration anomaly-detection system for predictive and preventative maintenance of industrial equipment.