These systems could include customer-operated checkout terminals, security cameras, video conferencing systems and robotic systems such as lawn mowers and cleaning equipment, Renesas said.
A combination of RZ/V visual AI processors from Renesas and the Syntiant NDP120 Neural Decision Processor provides voice and image processing capabilities.
It features "always-on" functionality with voice-triggered activation from standby mode to perform object recognition, facial recognition, and other vision-based tasks.
"We anticipate that demand for multimodal systems that use multiple streams of input information – both image and voice – will increase moving forward as a way to improve both ease of use and safety," said Hiroto Nitta, a senior vice president at Renesas, in a statement.
Syntiant CEO Kurt Busch said: "We’ve already shipped more than 15 million units of our deep learning NDPs globally to enable always-on voice in a wide variety of consumer and industrial IoT applications. Our collaboration with Renesas delivers a powerful, low-power voice and image solution that is certain to accelerate traction among a global customer base in a variety of devices and use cases."
The reference design for the new multimodal AI subsystem is available now, including circuit diagrams and BOM lists.
Related links and articles: