Vesper and DSP Group Demo Near-Zero-Power Voice-Activation for Battery-Powered Devices at CES 2017

January 16 2017, 04:00
During CES 2017, advanced acoustic sensors specialist Vesper, together with DSP Group, global provider of wireless chipset solutions for converged communications, and Sensory, a leading voice interface and keyword-detect algorithm company, have demonstrated a turnkey development platform that boasts the lowest overall power consumption for far-field always-listening voice interfaces. At CES, DSP Group also unveiled its new DBMD5 audio SoC built to drive clearer human-machine voice interactions.

The Vesper-DSP Group-Sensory integrated development platform features Sensory’s voice algorithms, enabling ultra-low-power consumer electronics that wake at voice input. This platform is the first to achieve overall power consumption low enough to enable battery-powered always-listening far-field systems.

“Today consumers who want to turn on their battery-powered smart speakers, TV remotes, smart home systems and Internet of Things (IoT) devices have to push a button to wake their device from sleep. This limits consumers’ ability to interact seamlessly and naturally with their devices, leaving them tethered to touch,” says Matt Crowley, CEO, Vesper. “The Vesper-DSP Group-Sensory development platform offers an alternative technology based on the fundamentally different physics of piezoelectric materials that wakes devices from sleep, while sipping mere microwatts of power. Due to the rugged nature of piezoelectric microphones, this platform is also ideal for systems that need to survive outdoors or in harsh environments.”

Crowley added, “The Vesper-DSP Group-Sensory wake-on-sound platform consumes 5x less power than existing approaches, potentially allowing products to run for years rather than months without battery replacement.”

The new development platform, demonstrated at CES 2017 for the first time, integrates Vesper’s VM1010 wake-on-sound piezoelectric MEMS microphone with DSP Group’s DBMD4, an ultra-low-power, always-on voice and audio processor based on Sensory’s Truly Handsfree voice control embedded algorithms. The platform gives developers the ability to initiate voice processing through Sensory’s wake-up word technology, which ensures that only a specific trigger word activates the device.

“Our development platform enables and dramatically accelerates time to market for far-field voice-controlled battery-powered consumer electronics,” says Ofer Elyakim, CEO, DSP Group. “It gives OEMs and integrators a fully integrated solution for consumer electronics that actively listen and sense both voice activity and commands while in near-zero-power mode, alleviating battery strain, improving device usability, and extending battery life.”

“Voice-activated battery-powered consumer electronics, such as smart speakers and TV remotes, are proliferating,” says Todd Mozer, CEO, Sensory Inc. “The Vesper-DSP Group-Sensory development platform — which features the same Sensory TrulyHandsfree voice activation algorithms that have already shipped in over 1 billion devices — is a major advancement in speeding the design-to-deployment cycle of keyword-activated battery-powered electronics.”

DSP Group New DBMD5 Audio SoC 
During CES 2017, DSP Group unveiled its new DBMD5 audio SoC built to drive clearer human-machine voice interactions in microphone-equipped devices. By leveraging DBMD5 with HDClear technology to support hands-free device control, manufacturers can now add a voice-user interface (VUI) to their products for accuracy in high-noise environments along with control over voice triggers and barge-in capabilities.

“Adoption of voice-enabled applications is growing fast. Whether it’s for mobile or a home automation assistant, people crave voice interactions, and we’re perfecting that,” says Ofer Elyakim, CEO of DSP Group. “The voice enhancement processing integrated in our DBMD5 chip allows devices to actively listen for the right voice commands and process incoming triggers, enabling clearer communication for the end user. We believe that our new chip solution will be instrumental in the evolution of voice as the default user interface.”

”When integrated into microphone-enabled devices, DBMD5 leverages voice enhancement algorithms to achieve more effective voice isolation in surrounding environments. Not only does DBMD5 ensure that your voices will be heard, but it also safeguards your device battery life. Due to its low-power consumption, you can easily wake up a portion of your device or system while other power-hungry components stay in sleep mode during voice sensing." 

The DBMD5 solution offers sophisticated voice enhancement algorithms, including echo cancellation, noise suppression, beam forming and far-field support. Its programmable dual-core DSP supports digital and analog microphones, incorporating various application processor interfaces such SPI, I2C, UART and SLIMbus, while a complete suite of drivers allow rapid development and fast time-to-market. | |
related items