This paper showcases how dialog definition, management, and domain information can be packaged in a uniform, ontology-based model that drives a dialog manager.
Table of contents
- Dialog scenario
- Knowledge & reasoning
- System architecture
- Ontology-based dialog modeling
- Supported Voice Assistants
- Conclusion and outlook
The Internet of Things is transforming the way we live, work and play. As connectivity moves into a range of home devices, applications and services, so do the customer expectations to experience on-market voice assistant (VA) capabilities during driving. With the EB Voice Assistant solution, we introduce a novel voice dialog framework for in-vehicle infotainment (IVI) applications. Our solution supports local creation and test of dialog models, as well as their deployment for on-market VA platforms like Amazon Alexa or Google Assistant. It extends the built-in capabilities of the existing VAs by offering modeling means for natural dialog and for tightly linking dialog knowledge with external data. With EB’s object-oriented and modular architecture, the above framework allows customers to have ﬂ exible, faster, reliable and continuous VA integrations into their IVI platforms during the whole project lifecycle.
Elektrobit’s end-to-end HMI tool: EB GUIDE