Touchscreen sensor maker Synaptics has unveiled a new family of AS3xx chips that enable a wide variety of voice-enabled smart home hubs and other appliances. The idea is to deliver more processing power at the edge of the network so we can have smarter and smarter devices in the internet of things (IoT).
Synaptics said the Smart Edge AudioSmart family is a set of system-on-chip (SoCs) offerings that include neural network acceleration, proprietary wake word engine, and advanced far-field voice processing. These technologies can be used in smart home hubs, Wi-Fi repeaters, speakers, and other appliances. The company made the announcement at CES 2019, the big tech trade show in Las Vegas this week.
The first chip, AudioSmart AS371, is available in samples now and incorporates a powerful machine-learning engine with SyNAP (Synaptics Neural Network Acceleration and Processing) technology.
“Intelligence at the edge begins in the Smart Home, where privacy is paramount, and with voice as the fastest-growing and most natural human interface,” said Huibert Verhoeven, senior vice president and general manager of the IoT division at Synaptics, in a statement. “Our cutting-edge voice processing technology and SyNAP integration not only provides unmatched performance and security, it opens numerous new opportunities across consumer IoT products, spanning speakers, displays, set-top boxes, thermostats, lighting, Wi-Fi repeaters, home appliances, and much more.”
Indeed, intelligence at the edge results in an enhanced user experience through better response times and robustness. For example, performing Automated Speech Recognition (ASR) and Natural Language Understanding (NLU) locally on-device ensures core Smart Home voice control works when there is poor or intermittent internet connectivity.
SyNAP enables advanced features such as user identification and behavioral prediction, which allows voice assistants to perform ambient computing and enables a more intuitive interaction with users.
In this era of being “always on” and connected — amplified by an ever-growing set of devices within the Smart Home — your device and data security is only as strong as your weakest link. Ensuring a high level of device and system security is a fundamental tenet of Synaptics’ AudioSmart AS3xx family of SoCs, with precautions ranging from a dedicated security processor to architecting every element of the SoC and system implementation, the company said.
The AS371 solution with SyNAP on-device intelligence enhances consumer privacy by greatly reducing the need to continuously send personal data to the cloud. SyNAP also complies with Europe’s tough privacy law, the General Data Protection Regulation (GDPR).
The far-field voice processing and wake word technology improves voice pick-up in noisy, real-world conditions and barge-in capabilities during very loud playback. Through in-house design of the SoC, wake word engine, voice pre-processing and playback enhancement, Synaptics has optimized the complete system to achieve the highest possible far-field voice performance at affordable consumer electronics price points.
While the AS371 is sampling now, the AS390 (for voice-enabled devices with displays), the AS350 (for voice-enabled low-power devices), and the AS320 (for voice-enabled microcontroller-based devices) will all be available in sample quantities in the first quarter of 2019.