Voice-controlled in-vehicle infotainment system
1University of Oulu, Faculty of Information Technology and Electrical Engineering, Department of Information Processing Science, Information Processing Science
|Online Access:||PDF Full Text (PDF, 2 MB)|
|Persistent link:|| http://urn.fi/URN:NBN:fi:oulu-202004181476
Oulu : J. Mourujärvi,
|Publish Date:|| 2020-04-20
|Thesis type:||Master's thesis
Sojan Kudakacheril, Arun
Bani Jamali, Ahmad
Speech is a form of a human to human communication that can convey information in a context-rich way that is natural to humans. The naturalness enables us to speak while doing other things, such as driving a vehicle. With the advancement of computing technologies, more and more personal services are introduced for the in-vehicle environment. A limiting factor for these advancements is the impact they cause towards driver distraction with the increased cognitive stress load. This has led to developing in-vehicle devices and applications with a heightened focus on lessening distraction.
Amazon Alexa is a natural language processing system that enables its users to receive information and operate smart devices with their voices. This Master’s thesis aims to demonstrate how Alexa could be utilized when operating the in-vehicle infotainment (IVI) systems. This research was conducted by utilizing the design science research methodology. The feasibility of voice-based interaction was assessed by implementing the system as a demonstrable use-case in collaboration with the APPSTACLE project. Prior research was gathered by conducting a literature review on voice-based interaction and its integration to the vehicular domain. The system was designed by applying existing theories together with the requirements of the application domain.
The designed system utilized the Amazon Alexa ecosystem and AWS services to provide the vehicular environment with new functionalities. Access to cloud-based speech processing and decision-making makes it possible to design an extendable speech interface where the driver can carry out secondary tasks by using their voice, such as requesting navigation information. The evaluation was done by comparing the system’s performance against the derived requirements.
With the results of the evaluation process, the feasibility of the system could be assessed against the objectives of the study: The resulting artefact enables the user to operate the in-vehicle infotainment system while focusing on a separate task. The research proved that speech interfaces with modern technology can improve the handling of secondary tasks while driving, and the resulting system was operable without introducing additional distractions to the driver. The resulting artefact can be integrated into similar systems and used as a base tool for future research on voice-controlled interfaces.
© Jere Mourujärvi, 2020. This publication is copyrighted. You may download, display and print it for your own personal use. Commercial use is prohibited.