Spoken Language Understanding on the Edge
This work addresses the problem of enabling efficient and private SLU on resource-constrained IoT devices for users in edge computing scenarios, though it is incremental as it builds on existing SLU methods.
The paper tackled the challenge of performing Spoken Language Understanding (SLU) on small IoT devices by designing an embedded, private-by-design system that achieves performance on par with cloud-based commercial solutions, and they released datasets for reproducibility and community use.
We consider the problem of performing Spoken Language Understanding (SLU) on small devices typical of IoT applications. Our contributions are twofold. First, we outline the design of an embedded, private-by-design SLU system and show that it has performance on par with cloud-based commercial solutions. Second, we release the datasets used in our experiments in the interest of reproducibility and in the hope that they can prove useful to the SLU community.