Renesas and Syntiant are teaming up to develop a new processor that will enable voice and computer vision utilities in edge devices. The solution blends an RZ/V Series microprocessor unit (MPU) from Renesas with the NDP120 Neural Decision Processor from Syntiant.
The NDP120 offers a slew of voice-based features, including speaker recognition and multiple wake words. Those features can then be used to activate and control computer vision systems when paired with the RZ/V Series MPUs.
The two companies suggested that their joint solution will speed up the development times of new computer vision applications and allow developers to bring products to market more quickly. They noted that voice activation will reduce power consumption when a device is in standby mode, since a device can be easily reactivated with a simple voice trigger. As a result, computer vision functions such as facial recognition, object recognition, and event detection can be carried out more efficiently at the edge.
Renesas and Syntiant believe that their solution is well-suited to a range of different industries. The technology can be used in any device with a camera, including self-checkout machines and smart appliances in addition to more conventional security cameras.
“Voice-based user interfaces will make it possible for customers to deliver new user experiences that bring the next generation of innovative ideas from concept to reality,” said Syntiant CEO Kurt Busch.
“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,” added Renesas SVP and SoC Business Head Hiroto Nitta. “We will accelerate the adoption of low-power, ultra-small smart voice AI technology in embedded systems and deliver new combined solutions to customers globally.”
The Syntiant and Renesas reference design has now been made available to interested customers. Renesas released an RZ/A2M processor to support embedded AI applications back in 2018. In the meantime, Grand View Research has predicted that the computer vision market will reach $19.1 billion by 2027.
(Originally posted on FindBiometrics)