At this week’s Consumer Electronics Show in Las Vegas, Californian semiconductor IP firm Ceva unveiled its Senslinq integrated hardware IP and software platform that aggregates sensor fusion, sound and connectivity technologies to enable contextually aware IoT devices.
 
Contextual awareness is rapidly becoming a mandatory feature of many devices such as smartphones, laptops, AR and VR headsets, robots, hearables and wearables, driven by OEMs and IT companies looking to add value and enhance the user experience.
 
The Senslinq platform streamlines the development of these devices by centralising the workloads that require an intimate understanding of the physical behaviour and anomalies of sensors. It collects data from multiple sensors within a device, including microphones, radar, inertial measurement units, environmental sensors and time of flight, and conducts front-end signal processing such as noise suppression and filtering on these data.
 
Then, applying algorithms, Senslinq creates context enablers such as activity classification, voice and sound detection, and presence and proximity detection. These context enablers can then be fused on-device or otherwise sent wirelessly (Bluetooth, wifi or NB-IoT) to a local edge computer or the cloud for determining and adapting the device to the environment in which it operates.
 
The platform incorporates the hardware IP and software components required to enable contextually aware IoT devices. The customisable hardware reference design is composed of three pillars connected using standard system interfaces:

• Arm or Risc-V MCU
• Ceva-BX DSPs
• Wireless connectivity island, such as RivieraWaves Bluetooth, wifi or Dragonfly NB-IoT platforms, or other connectivity standards provided by the user or third parties.

The software is comprised of a portfolio of ready-to-use software libraries from Ceva and its ecosystem partners, which includes Hillcrest Labs MotionEngine software packages for sensor fusion and activity classification in mobile, wearables, hearables, robots and more, and ClearVox front-end voice processing, WhisPro speech recognition, and DSP and AI libraries. There are also third-party software components for active noise cancellation, sound sensing, 3D audio and more.

The platform is accompanied by the Senslinq framework, a Linux-based hardware abstraction layer reference code and APIs for data and control exchange between the multiple processors and the various sensors.

“Ceva has consistently expanded its product portfolio in recent years both through organic investment and M&A, towards the strategic goal of driving market innovation in wireless connectivity and smart sensing,” said Erez Bar-Niv, CTO of Ceva. “Contextual awareness, which fuses motion, sound, environmental and other sensor-created data, provides the opportunity to capitalise on our technology excellence. Senslinq frees up our customers from having to understand the physical behaviour of sensors and the connectivity channels, allowing them to focus on the applications and advanced services possible with a context-aware device.”

Senslinq will be available in the second quarter of 2020.

Ceva is a licensor of wireless connectivity and smart sensing technologies. It offers digital signal processors, AI processors, wireless platforms and software for sensor fusion, image enhancement, computer vision, voice input and artificial intelligence.