System Imperatives for Audio and Video AI at the Edge

At long last, we are past the hype stage for media AI. Audio and video machine learning are becoming common tools for embedded hardware and software engineers. But are designers really using ML right? Are architects intelligently partitioning ML solutions between the cloud, user edge platforms and embedded compute components? Do they understand how to effectively combine deep-learning-based and conventional audio and video algorithms? Are they creating interfaces that enable their products to evolve in response to market needs? In this talk, we explore the conflicting currents pushing ML to the cloud and to the edge. We examine how the challenges of power, cost, compute, memory footprint, security and application autonomy affect different classes of audio and video devices and systems. We outline strategies for teams planning new ML hardware and software to avoid some of the critical pitfalls and achieve better balance between time-to-market, application flexibility and system efficiency.