Data Center Audio/Video Intelligence on Device (DAVID) -- An Edge-AI Platform for Smart-Toys
This work addresses privacy and efficiency issues for smart toy manufacturers and users by enabling edge AI processing, though it is incremental as it builds on existing edge computing and neural network technologies.
The paper tackles the challenge of implementing advanced AI capabilities in smart toys by introducing the DAVID platform, which processes audio and video data on-device using neural inference models, resulting in a system that avoids transmitting personally identifiable information and ensures compliance with data protection regulations.
An overview is given of the DAVID Smart-Toy platform, one of the first Edge AI platform designs to incorporate advanced low-power data processing by neural inference models co-located with the relevant image or audio sensors. There is also on-board capability for in-device text-to-speech generation. Two alternative embodiments are presented: a smart Teddy-bear, and a roving dog-like robot. The platform offers a speech-driven user interface and can observe and interpret user actions and facial expressions via its computer vision sensor node. A particular benefit of this design is that no personally identifiable information passes beyond the neural inference nodes thus providing inbuilt compliance with data protection regulations.